Index _ | A | B | C | D | E | F | G | H | I | K | L | M | N | O | P | Q | R | S | T | U | V | W | Z _ _async_worker() (in module agilerl.vector.pz_async_vec_env) A accum_logs() (agilerl.utils.log_utils.DistributeCombineLogs method) action_entropy() (agilerl.networks.actors.StochasticActor method) action_log_prob() (agilerl.networks.actors.StochasticActor method) action_noise() (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.td3.TD3 method) action_space (agilerl.vector.pz_vec_env.PettingZooVecEnv property) action_space() (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) activation (agilerl.modules.cnn.EvolvableCNN property) (agilerl.modules.gpt.EvolvableGPT property) (agilerl.modules.lstm.EvolvableLSTM property) (agilerl.modules.mlp.EvolvableMLP property) (agilerl.modules.multi_input.EvolvableMultiInput property) (agilerl.networks.base.EvolvableNetwork property) (agilerl.wrappers.make_evolvable.MakeEvolvable property) activation_mutation() (agilerl.hpo.mutation.Mutations method) add() (agilerl.components.replay_buffer.MultiStepReplayBuffer method) (agilerl.components.replay_buffer.PrioritizedReplayBuffer method) (agilerl.components.replay_buffer.ReplayBuffer method) (agilerl.components.rollout_buffer.RolloutBuffer method) (agilerl.models.algo.AlgorithmRegistry method) add_block() (agilerl.modules.resnet.EvolvableResNet method) (agilerl.modules.simba.EvolvableSimBa method) add_channel() (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.resnet.EvolvableResNet method) add_cnn_channel() (agilerl.wrappers.make_evolvable.MakeEvolvable method) add_cnn_layer() (agilerl.wrappers.make_evolvable.MakeEvolvable method) add_decoder_layer() (agilerl.modules.bert.EvolvableBERT method) add_encoder_layer() (agilerl.modules.bert.EvolvableBERT method) add_fitness() (agilerl.metrics.BaseMetrics method) add_latent_node() (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.networks.base.EvolvableNetwork method) add_layer() (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) add_mlp_layer() (agilerl.wrappers.make_evolvable.MakeEvolvable method) add_mlp_node() (agilerl.wrappers.make_evolvable.MakeEvolvable method) add_node() (agilerl.modules.bert.EvolvableBERT method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.simba.EvolvableSimBa method) add_placeholder_value() (in module agilerl.utils.algo_utils) add_scores() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.metrics.BaseMetrics method) add_system_configs() (in module agilerl.utils.ilql_utils) additional_metrics (agilerl.metrics.BaseMetrics property) Agent (class in agilerl.arena.inference) AgentMetrics (class in agilerl.metrics) agents (agilerl.population.Population property) AgentWrapper (class in agilerl.wrappers.agent) agilerl.utils.probe_envs_llm module algo_class() (agilerl.models.algo.AlgorithmSpec class method) (agilerl.models.algo.LLMAlgorithmSpec class method) (agilerl.models.algo.MultiAgentRLAlgorithmSpec class method) (agilerl.models.algo.RLAlgorithmSpec class method) ALGO_REGISTRY (in module agilerl.models.algo) AlgorithmRegistry (class in agilerl.models.algo) AlgorithmSpec (class in agilerl.models.algo) all_below() (agilerl.population.Population method) all_registered() (agilerl.algorithms.core.registry.MutationRegistry method) apply_chat_template() (in module agilerl.utils.llm_utils) apply_gaussian_init() (agilerl.modules.base.EvolvableModule static method) apply_image_normalization() (in module agilerl.utils.algo_utils) apply_mask() (agilerl.networks.actors.EvolvableDistribution method) architecture_mutate() (agilerl.hpo.mutation.Mutations method) ARENA_REGISTRY (in module agilerl.arena.models) ArenaAPIError (class in agilerl.arena.exceptions) ArenaAuthError (class in agilerl.arena.exceptions) ArenaClient (class in agilerl.arena.client) ArenaError (class in agilerl.arena.exceptions) ArenaInferenceError (class in agilerl.arena.exceptions) ArenaOAuth2 (class in agilerl.arena.auth) ArenaTimeoutError (class in agilerl.arena.exceptions) ArenaTrainer (class in agilerl.training.trainer) ArenaTrainingError (class in agilerl.arena.exceptions) ArenaValidationError (class in agilerl.arena.exceptions) assemble_grouped_outputs() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) assemble_shared_inputs() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) AsyncAgentsWrapper (class in agilerl.wrappers.agent) AsyncPettingZooVecEnv (class in agilerl.vector.pz_async_vec_env) aux_metric_name (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) B BanditEnv (class in agilerl.wrappers.learning) BanditEnvSpec (class in agilerl.models.env) BASE_URL (agilerl.arena.client.ArenaClient attribute) BaseMetrics (class in agilerl.metrics) Block (class in agilerl.modules.gpt) build_algorithm() (agilerl.models.algo.AlgorithmSpec method) (agilerl.models.algo.LLMAlgorithmSpec method) (agilerl.models.algo.MultiAgentRLAlgorithmSpec method) (agilerl.models.algo.RLAlgorithmSpec method) build_feature_extractor() (agilerl.modules.multi_input.EvolvableMultiInput method) build_net_config() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) build_network_head() (agilerl.networks.actors.DeterministicActor method) (agilerl.networks.actors.StochasticActor method) (agilerl.networks.base.EvolvableNetwork method) (agilerl.networks.q_networks.ContinuousQNetwork method) (agilerl.networks.q_networks.QNetwork method) (agilerl.networks.q_networks.RainbowQNetwork method) (agilerl.networks.value_networks.ValueNetwork method) build_networks() (agilerl.modules.bert.EvolvableBERT method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) build_rms() (agilerl.wrappers.agent.RSNorm static method) C Cache (class in agilerl.utils.cache) calc_extracted_features_dim() (agilerl.modules.multi_input.EvolvableMultiInput method) calc_max_kernel_sizes() (agilerl.wrappers.make_evolvable.MakeEvolvable method) calc_stride_size_ranges() (agilerl.wrappers.make_evolvable.MakeEvolvable method) calculate_vectorized_scores() (in module agilerl.utils.utils) call() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) call_async() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) call_wait() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) cat() (agilerl.components.data.Transition method) CausalSelfAttention (class in agilerl.modules.gpt) change_activation() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.base.EvolvableWrapper method) (agilerl.modules.base.ModuleDict method) (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.dummy.DummyEvolvable method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.modules.resnet.EvolvableResNet method) (agilerl.modules.simba.EvolvableSimBa method) (agilerl.networks.base.EvolvableNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) change_cnn_kernel() (agilerl.wrappers.make_evolvable.MakeEvolvable method) change_kernel() (agilerl.modules.cnn.EvolvableCNN method) check_encoder_sparsity_fast_path() (agilerl.modules.bert.EvolvableBERT method) check_policy_on_policy_with_probe_env() (in module agilerl.utils.probe_envs) check_policy_q_learning_with_probe_env() (in module agilerl.utils.probe_envs) (in module agilerl.utils.probe_envs_ma) check_q_learning_with_probe_env() (in module agilerl.utils.probe_envs) CheckEvent (class in agilerl.arena.stream) checkpoint_dict() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method) chkpt_attribute_to_device() (in module agilerl.utils.algo_utils) CISPO (class in agilerl.algorithms.cispo) clean_up() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ilql.ILQL method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) clear() (agilerl.components.replay_buffer.MultiStepReplayBuffer method) (agilerl.components.replay_buffer.PrioritizedReplayBuffer method) (agilerl.components.replay_buffer.ReplayBuffer method) (agilerl.metrics.AgentMetrics method) (agilerl.metrics.BaseMetrics method) (agilerl.metrics.MultiAgentMetrics method) clear_agent_metrics() (agilerl.population.Population method) clone() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ilql.ILQL method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.modules.base.EvolvableModule method) (agilerl.modules.base.ModuleDict method) (agilerl.networks.actors.EvolvableDistribution method) (agilerl.wrappers.agent.AgentWrapper method) clone_llm() (in module agilerl.utils.algo_utils) close() (agilerl.arena.client.ArenaClient method) (agilerl.arena.inference.Agent method) (agilerl.arena.output.StreamRichRenderer method) (agilerl.arena.stream.NDJsonStream method) (agilerl.logger.CSVLogger method) (agilerl.logger.Logger method) (agilerl.logger.StdOutLogger method) (agilerl.logger.TensorboardLogger method) (agilerl.logger.WandbLogger method) (agilerl.vector.dummy_vec_env.DummyVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) close_extras() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) cnn_init_dict (agilerl.modules.multi_input.EvolvableMultiInput property) CnnSpec (class in agilerl.models.networks) collect() (agilerl.arena.stream.NDJsonStream method) collect_rollouts() (in module agilerl.rollouts) collect_rollouts_recurrent() (in module agilerl.rollouts) compare_responses() (in module agilerl.utils.llm_utils) compile_model() (in module agilerl.utils.evolvable_networks) compute_returns_and_advantages() (agilerl.components.rollout_buffer.RolloutBuffer method) concatenate_experiences_into_batches() (in module agilerl.utils.algo_utils) concatenate_spaces() (in module agilerl.utils.algo_utils) concatenate_tensors() (in module agilerl.utils.algo_utils) ConditionalTargetEnv (class in agilerl.utils.probe_envs_llm) CONFIG_DIR (agilerl.arena.client.ArenaClient attribute) CONFIG_FILE (agilerl.arena.client.ArenaClient attribute) config_from_dict() (in module agilerl.utils.evolvable_networks) configure() (agilerl.arena.auth.ArenaOAuth2 class method) (agilerl.arena.client.ArenaClient class method) configure_optimizers() (agilerl.modules.gpt.EvolvableGPT method) ConstantRewardContActionsEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ConstantRewardContActionsImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ConstantRewardEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ConstantRewardImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ConstantTargetEnv (class in agilerl.utils.probe_envs_llm) construct_custom_env_fn() (agilerl.models.env.GymEnvSpec static method) (agilerl.models.env.PzEnvSpec static method) contains_moduledict() (in module agilerl.utils.evolvable_networks) ContinuousQNetwork (class in agilerl.networks.q_networks) ContinuousQNetworkSpec (class in agilerl.models.networks) convert_key() (agilerl.utils.log_utils.DistributeCombineLogs method) convert_path() (in module agilerl.utils.ilql_utils) copy_attributes() (agilerl.algorithms.cispo.CISPO static method) (agilerl.algorithms.core.base.EvolvableAlgorithm static method) (agilerl.algorithms.cqn.CQN static method) (agilerl.algorithms.ddpg.DDPG static method) (agilerl.algorithms.dpo.DPO static method) (agilerl.algorithms.dqn.DQN static method) (agilerl.algorithms.dqn_rainbow.RainbowDQN static method) (agilerl.algorithms.grpo.GRPO static method) (agilerl.algorithms.gspo.GSPO static method) (agilerl.algorithms.ippo.IPPO static method) (agilerl.algorithms.maddpg.MADDPG static method) (agilerl.algorithms.matd3.MATD3 static method) (agilerl.algorithms.neural_ts_bandit.NeuralTS static method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB static method) (agilerl.algorithms.ppo.PPO static method) (agilerl.algorithms.ppo_llm.PPO static method) (agilerl.algorithms.reinforce_llm.REINFORCE static method) (agilerl.algorithms.sft.SFT static method) (agilerl.algorithms.td3.TD3 static method) CosineLRScheduleConfig (class in agilerl.utils.algo_utils) count_parameters() (agilerl.modules.bert.EvolvableBERT method) count_tag (agilerl.utils.log_utils.DistributeCombineLogs attribute) CQN (class in agilerl.algorithms.cqn) create_cnn() (agilerl.modules.cnn.EvolvableCNN method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) (in module agilerl.utils.evolvable_networks) create_dataloader() (agilerl.components.sampler.Sampler class method) create_dataset() (agilerl.arena.client.ArenaClient method) create_lstm() (agilerl.modules.lstm.EvolvableLSTM method) create_mask() (agilerl.modules.bert.EvolvableBERT method) create_mlp() (agilerl.networks.base.EvolvableNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) (in module agilerl.utils.evolvable_networks) create_model_from_name_or_path() (in module agilerl.utils.llm_utils) create_population() (in module agilerl.utils.utils) create_project() (agilerl.arena.client.ArenaClient method) create_resnet() (agilerl.modules.resnet.EvolvableResNet method) (in module agilerl.utils.evolvable_networks) create_rollout_buffer() (agilerl.algorithms.ppo.PPO method) create_shared_memory() (in module agilerl.vector.pz_async_vec_env) create_simba() (in module agilerl.utils.evolvable_networks) create_warmup_cosine_scheduler() (in module agilerl.utils.algo_utils) crop_block_size() (agilerl.modules.gpt.EvolvableGPT method) CSVLogger (class in agilerl.logger) D dataset_backed_rollout (agilerl.models.env.LLMEnvSpec property) dataset_exists() (agilerl.arena.client.ArenaClient method) DatasetEnv (class in agilerl.llm_envs) DDPG (class in agilerl.algorithms.ddpg) decode() (agilerl.modules.bert.EvolvableBERT method) delete_dataset() (agilerl.arena.client.ArenaClient method) delete_environment() (agilerl.arena.client.ArenaClient method) delete_project() (agilerl.arena.client.ArenaClient method) delete_session() (agilerl.arena.inference.Agent method) deploy_agent() (agilerl.arena.client.ArenaClient method) detect_architecture() (agilerl.wrappers.make_evolvable.MakeEvolvable method) DeterministicActor (class in agilerl.networks.actors) DeterministicActorSpec (class in agilerl.models.networks) device (agilerl.components.data.Transition property) (agilerl.wrappers.agent.AgentWrapper property) device_login() (agilerl.arena.auth.ArenaOAuth2 method) disable_mutations() (agilerl.modules.base.EvolvableModule method) disassemble_grouped_outputs() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) DiscountedRewardContActionsEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) DiscountedRewardContActionsImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) DiscountedRewardEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) DiscountedRewardImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) DistributeCombineLogs (class in agilerl.utils.log_utils) download_experiment_metrics() (agilerl.arena.client.ArenaClient method) DPO (class in agilerl.algorithms.dpo) DQN (class in agilerl.algorithms.dqn) dtype (agilerl.algorithms.core.registry.RLParameter attribute) DummyEvolvable (class in agilerl.modules.dummy) DummyVecEnv (class in agilerl.vector.dummy_vec_env) dump() (agilerl.utils.cache.Cache method) dumps() (agilerl.components.data.Transition method) duplicate_environment_version() (agilerl.arena.client.ArenaClient method) E emit_csv_preview() (in module agilerl.arena.output) emit_result() (in module agilerl.arena.output) enable_cli_mode() (agilerl.arena.exceptions.ArenaError class method) encode() (agilerl.modules.bert.EvolvableBERT method) encoder_config (agilerl.networks.base.EvolvableNetwork property) entropy() (agilerl.networks.actors.EvolvableDistribution method) environment_exists() (agilerl.arena.client.ArenaClient method) error (agilerl.arena.stream.NDJsonStream property) ErrorEvent (class in agilerl.arena.stream) estimate_mfu() (agilerl.modules.gpt.EvolvableGPT method) eval_network_name() (agilerl.algorithms.core.registry.NetworkGroup method) eval_policy_network_ids() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) eval_rows() (agilerl.population.MetricsReport method) evaluate_actions() (agilerl.algorithms.ppo.PPO method) evolvable_attributes() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.wrappers.agent.AgentWrapper method) evolvable_modules() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.base.ModuleDict method) EvolvableAlgorithm (class in agilerl.algorithms.core.base) EvolvableBERT (class in agilerl.modules.bert) EvolvableCNN (class in agilerl.modules.cnn) EvolvableDistribution (class in agilerl.networks.actors) EvolvableGPT (class in agilerl.modules.gpt) EvolvableLSTM (class in agilerl.modules.lstm) EvolvableMLP (class in agilerl.modules.mlp) EvolvableModule (class in agilerl.modules.base) EvolvableMultiInput (class in agilerl.modules.multi_input) EvolvableNetwork (class in agilerl.networks.base) EvolvableResNet (class in agilerl.modules.resnet) EvolvableSimBa (class in agilerl.modules.simba) EvolvableWrapper (class in agilerl.modules.base) experience_to_tensors() (in module agilerl.utils.algo_utils) extract_action_masks() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) extract_agent_masks() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) extract_features() (agilerl.networks.base.EvolvableNetwork method) extract_filename() (in module agilerl.arena.utils) extract_inactive_agents() (agilerl.wrappers.agent.AsyncAgentsWrapper method) F fields() (agilerl.components.data.Transition class method) filter_mutation_methods() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.base.ModuleDict method) finalize_training_step() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.metrics.BaseMetrics method) FinetuningNetworkSpec (class in agilerl.models.networks) finish() (agilerl.population.Population method) fitness (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) FixedObsPolicyContActionsEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) FixedObsPolicyContActionsImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) FixedObsPolicyEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) FixedObsPolicyImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) flatten_experiences() (in module agilerl.utils.algo_utils) format_shared_critic_encoder() (in module agilerl.utils.algo_utils) forward() (agilerl.algorithms.ilql.ILQL method) (agilerl.modules.base.EvolvableModule method) (agilerl.modules.bert.EvolvableBERT method) (agilerl.modules.bert.PositionalEncoder method) (agilerl.modules.bert.PositionalEncoding method) (agilerl.modules.bert.TokenEmbedding method) (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.custom_components.GumbelSoftmax method) (agilerl.modules.dummy.DummyEvolvable method) (agilerl.modules.gpt.Block method) (agilerl.modules.gpt.CausalSelfAttention method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.gpt.LayerNorm method) (agilerl.modules.gpt.MLP method) (agilerl.modules.gpt.PositionalEncoding method) (agilerl.modules.gpt.TokenEmbedding method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.modules.resnet.EvolvableResNet method) (agilerl.modules.simba.EvolvableSimBa method) (agilerl.networks.actors.DeterministicActor method) (agilerl.networks.actors.EvolvableDistribution method) (agilerl.networks.actors.StochasticActor method) (agilerl.networks.q_networks.ContinuousQNetwork method) (agilerl.networks.q_networks.QNetwork method) (agilerl.networks.q_networks.RainbowQNetwork method) (agilerl.networks.value_networks.ValueNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) forward_head() (agilerl.networks.base.EvolvableNetwork method) from_any() (agilerl.components.data.Transition method) from_csv() (agilerl.components.data.Transition method) from_dataclass() (agilerl.components.data.Transition method) from_h5() (agilerl.components.data.Transition method) from_json() (agilerl.components.data.Transition method) from_manifest() (agilerl.training.trainer.Trainer class method) from_modules() (agilerl.components.data.Transition method) from_namedtuple() (agilerl.components.data.Transition method) from_pandas() (agilerl.components.data.Transition method) from_parquet() (agilerl.components.data.Transition method) from_pretrained() (agilerl.modules.gpt.EvolvableGPT class method) from_pytree() (agilerl.components.data.Transition method) from_remote_init() (agilerl.components.data.Transition method) from_response_body() (agilerl.arena.exceptions.ArenaAPIError class method) (agilerl.arena.exceptions.ArenaTrainingError class method) from_schema() (agilerl.components.data.Transition method) from_struct_array() (agilerl.components.data.Transition method) from_tensordict() (agilerl.components.data.Transition class method) from_trainer_specs() (agilerl.models.manifest.TrainingManifest class method) from_tuple() (agilerl.components.data.Transition method) fromkeys() (agilerl.components.data.Transition method) G gather_if_zero3() (in module agilerl.utils.llm_utils) gather_logs() (agilerl.utils.log_utils.DistributeCombineLogs method) generate() (agilerl.arena.inference.Agent method) (agilerl.modules.gpt.EvolvableGPT method) generate_square_subsequent_mask() (agilerl.modules.bert.EvolvableBERT method) generate_stream() (agilerl.arena.inference.Agent method) get() (agilerl.components.data.Transition method) (agilerl.components.rollout_buffer.RolloutBuffer method) (agilerl.models.algo.AlgorithmRegistry method) get_action() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.arena.inference.Agent method) (agilerl.wrappers.agent.AgentWrapper method) (agilerl.wrappers.agent.AsyncAgentsWrapper method) (agilerl.wrappers.agent.RSNorm method) get_action_dim() (agilerl.algorithms.cispo.CISPO static method) (agilerl.algorithms.core.base.EvolvableAlgorithm static method) (agilerl.algorithms.cqn.CQN static method) (agilerl.algorithms.ddpg.DDPG static method) (agilerl.algorithms.dpo.DPO static method) (agilerl.algorithms.dqn.DQN static method) (agilerl.algorithms.dqn_rainbow.RainbowDQN static method) (agilerl.algorithms.grpo.GRPO static method) (agilerl.algorithms.gspo.GSPO static method) (agilerl.algorithms.ippo.IPPO static method) (agilerl.algorithms.maddpg.MADDPG static method) (agilerl.algorithms.matd3.MATD3 static method) (agilerl.algorithms.neural_ts_bandit.NeuralTS static method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB static method) (agilerl.algorithms.ppo.PPO static method) (agilerl.algorithms.ppo_llm.PPO static method) (agilerl.algorithms.reinforce_llm.REINFORCE static method) (agilerl.algorithms.sft.SFT static method) (agilerl.algorithms.td3.TD3 static method) get_activation() (in module agilerl.utils.evolvable_networks) get_attr() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) get_batch() (agilerl.components.segment_tree.MinSegmentTree method) (agilerl.components.segment_tree.SegmentTree method) (agilerl.components.segment_tree.SumSegmentTree method) get_batch_norm_layer() (in module agilerl.utils.evolvable_networks) get_cache() (agilerl.utils.cache.Cache method) get_conv_layer() (in module agilerl.utils.evolvable_networks) get_current_user() (agilerl.arena.client.ArenaClient method) get_deepest_head_config() (in module agilerl.utils.algo_utils) get_default_encoder_config() (in module agilerl.utils.evolvable_networks) get_default_project() (agilerl.arena.client.ArenaClient method) get_default_run_spec() (agilerl.arena.client.ArenaClient method) get_distribution() (agilerl.networks.actors.EvolvableDistribution method) get_env_defined_actions() (in module agilerl.utils.utils) get_eval_modules() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) get_experiences_samples() (in module agilerl.utils.algo_utils) get_group_id() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) get_hidden_state_architecture() (agilerl.algorithms.ppo.PPO method) get_hidden_states_shape_from_model() (in module agilerl.utils.algo_utils) get_histogram() (agilerl.metrics.AgentMetrics method) (agilerl.metrics.BaseMetrics method) (agilerl.metrics.MultiAgentMetrics method) get_hit_rate() (agilerl.utils.cache.Cache method) get_init_dict() (agilerl.modules.base.EvolvableModule method) (agilerl.networks.base.EvolvableNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) get_initial_hidden_state() (agilerl.algorithms.ppo.PPO method) get_inner_init_dict() (agilerl.modules.multi_input.EvolvableMultiInput method) get_input_size_from_space() (in module agilerl.utils.algo_utils) get_lr_names() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) get_mean() (agilerl.metrics.AgentMetrics method) (agilerl.metrics.MultiAgentMetrics method) get_minibatch_sequences() (agilerl.components.rollout_buffer.RolloutBuffer method) get_model_info() (agilerl.arena.client.ArenaClient method) get_module_dict() (in module agilerl.utils.evolvable_networks) get_mutation_methods() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.base.ModuleDict method) get_mutation_probs() (agilerl.modules.base.EvolvableModule method) get_nested_mean() (in module agilerl.utils.population_utils) get_network_id() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) get_normalization() (in module agilerl.utils.evolvable_networks) get_num_actions() (in module agilerl.utils.algo_utils) get_num_params() (agilerl.modules.gpt.EvolvableGPT method) get_obs_shape() (in module agilerl.utils.algo_utils) get_observations() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) get_output_dense() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.simba.EvolvableSimBa method) (agilerl.networks.value_networks.ValueNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) get_output_size_from_space() (in module agilerl.utils.algo_utils) get_placeholder_value() (in module agilerl.vector.pz_async_vec_env) get_policy() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) get_pooling() (in module agilerl.utils.evolvable_networks) get_session() (agilerl.arena.inference.Agent method) get_setup() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) get_state_dict() (in module agilerl.utils.llm_utils) get_state_dim() (agilerl.algorithms.cispo.CISPO static method) (agilerl.algorithms.core.base.EvolvableAlgorithm static method) (agilerl.algorithms.cqn.CQN static method) (agilerl.algorithms.ddpg.DDPG static method) (agilerl.algorithms.dpo.DPO static method) (agilerl.algorithms.dqn.DQN static method) (agilerl.algorithms.dqn_rainbow.RainbowDQN static method) (agilerl.algorithms.grpo.GRPO static method) (agilerl.algorithms.gspo.GSPO static method) (agilerl.algorithms.ippo.IPPO static method) (agilerl.algorithms.maddpg.MADDPG static method) (agilerl.algorithms.matd3.MATD3 static method) (agilerl.algorithms.neural_ts_bandit.NeuralTS static method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB static method) (agilerl.algorithms.ppo.PPO static method) (agilerl.algorithms.ppo_llm.PPO static method) (agilerl.algorithms.reinforce_llm.REINFORCE static method) (agilerl.algorithms.sft.SFT static method) (agilerl.algorithms.td3.TD3 static method) get_tensor_batch() (agilerl.components.rollout_buffer.RolloutBuffer method) get_training_fn() (agilerl.models.algo.AlgorithmSpec class method) get_training_kwargs() (agilerl.models.algo.AlgorithmSpec method) get_transformer_logs() (in module agilerl.utils.torch_utils) get_user_credits() (agilerl.arena.client.ArenaClient method) get_validated() (agilerl.arena.models.TrainingManifest class method) (agilerl.models.manifest.TrainingManifest class method) get_values_for_key() (in module agilerl.utils.population_utils) get_vect_dim() (in module agilerl.utils.algo_utils) GridNavigationEnv (class in agilerl.utils.probe_envs_llm) GRPO (class in agilerl.algorithms.grpo) GSPO (class in agilerl.algorithms.gspo) gumbel_softmax() (agilerl.modules.custom_components.GumbelSoftmax static method) GumbelSoftmax (class in agilerl.modules.custom_components) GymEnvSpec (class in agilerl.models.env) H handle_error() (in module agilerl.arena.output) handle_event() (agilerl.arena.output.StreamRichRenderer method) hard_update() (agilerl.algorithms.ilql.ILQL method) has_grouped_agents() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) head_config (agilerl.networks.base.EvolvableNetwork property) hidden_state_architecture (agilerl.modules.lstm.EvolvableLSTM property) hp_config (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) HyperparameterConfig (class in agilerl.algorithms.core.registry) I ILQL (class in agilerl.algorithms.ilql) increment_evo_step() (agilerl.population.Population method) increment_steps() (agilerl.metrics.BaseMetrics method) index (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) init_buffer() (agilerl.models.training.ReplayBufferSpec method) init_dicts (agilerl.modules.multi_input.EvolvableMultiInput property) init_n_step_buffer() (agilerl.models.training.ReplayBufferSpec method) init_params() (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) init_training_step() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.metrics.BaseMetrics method) init_wandb() (in module agilerl.utils.utils) init_weights_gaussian() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.modules.simba.EvolvableSimBa method) (agilerl.networks.base.EvolvableNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) (in module agilerl.utils.evolvable_networks) initialize_hidden_state() (agilerl.networks.base.EvolvableNetwork method) InProcessEnvClient (class in agilerl.llm_envs.openenv) inspect_attributes() (agilerl.algorithms.cispo.CISPO static method) (agilerl.algorithms.core.base.EvolvableAlgorithm static method) (agilerl.algorithms.cqn.CQN static method) (agilerl.algorithms.ddpg.DDPG static method) (agilerl.algorithms.dpo.DPO static method) (agilerl.algorithms.dqn.DQN static method) (agilerl.algorithms.dqn_rainbow.RainbowDQN static method) (agilerl.algorithms.grpo.GRPO static method) (agilerl.algorithms.gspo.GSPO static method) (agilerl.algorithms.ippo.IPPO static method) (agilerl.algorithms.maddpg.MADDPG static method) (agilerl.algorithms.matd3.MATD3 static method) (agilerl.algorithms.neural_ts_bandit.NeuralTS static method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB static method) (agilerl.algorithms.ppo.PPO static method) (agilerl.algorithms.ppo_llm.PPO static method) (agilerl.algorithms.reinforce_llm.REINFORCE static method) (agilerl.algorithms.sft.SFT static method) (agilerl.algorithms.td3.TD3 static method) IPPO (class in agilerl.algorithms.ippo) is_authenticated (agilerl.arena.client.ArenaClient property) is_box_space_ndim() (in module agilerl.utils.evolvable_networks) is_image_space() (in module agilerl.utils.algo_utils) (in module agilerl.utils.evolvable_networks) is_nested_scores() (agilerl.population.Population method) is_peft_model() (in module agilerl.utils.algo_utils) is_vector_space() (in module agilerl.utils.evolvable_networks) is_vectorized_experiences() (in module agilerl.utils.algo_utils) isroutine() (in module agilerl.utils.algo_utils) items() (agilerl.modules.base.ModuleDict method) (agilerl.utils.cache.Cache method) K kernel_size (agilerl.modules.cnn.EvolvableCNN property) key_in_nested_dict() (in module agilerl.utils.algo_utils) key_is_count() (agilerl.utils.log_utils.DistributeCombineLogs method) keys() (agilerl.utils.cache.Cache method) L label_logs() (in module agilerl.utils.log_utils) last_scalar_fitnesses (agilerl.population.Population property) layer_init() (in module agilerl.utils.evolvable_networks) LayerNorm (class in agilerl.modules.gpt) lazy_stack() (agilerl.components.data.Transition method) learn() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.wrappers.agent.AgentWrapper method) (agilerl.wrappers.agent.AsyncAgentsWrapper method) (agilerl.wrappers.agent.RSNorm method) learn_individual() (agilerl.algorithms.matd3.MATD3 method) list_checkpoints() (agilerl.arena.client.ArenaClient method) list_datasets() (agilerl.arena.client.ArenaClient method) list_environment_entrypoints() (agilerl.arena.client.ArenaClient method) list_environments() (agilerl.arena.client.ArenaClient method) list_experiment_metric_names() (agilerl.arena.client.ArenaClient method) list_experiments() (agilerl.arena.client.ArenaClient method) list_inference_deployments() (agilerl.arena.client.ArenaClient method) list_models() (agilerl.arena.client.ArenaClient method) list_projects() (agilerl.arena.client.ArenaClient method) list_resources() (agilerl.arena.client.ArenaClient method) list_sessions() (agilerl.arena.inference.Agent method) LLMAlgorithmSpec (class in agilerl.models.algo) LLMCompletionResult (class in agilerl.arena.inference) LLMEnvSpec (class in agilerl.models.env) LLMParams (class in agilerl.arena.inference) LLMResults (class in agilerl.arena.inference) load() (agilerl.algorithms.cispo.CISPO class method) (agilerl.algorithms.core.base.EvolvableAlgorithm class method) (agilerl.algorithms.cqn.CQN class method) (agilerl.algorithms.ddpg.DDPG class method) (agilerl.algorithms.dpo.DPO class method) (agilerl.algorithms.dqn.DQN class method) (agilerl.algorithms.dqn_rainbow.RainbowDQN class method) (agilerl.algorithms.grpo.GRPO class method) (agilerl.algorithms.gspo.GSPO class method) (agilerl.algorithms.ippo.IPPO class method) (agilerl.algorithms.maddpg.MADDPG class method) (agilerl.algorithms.matd3.MATD3 class method) (agilerl.algorithms.neural_ts_bandit.NeuralTS class method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB class method) (agilerl.algorithms.ppo.PPO class method) (agilerl.algorithms.ppo_llm.PPO class method) (agilerl.algorithms.reinforce_llm.REINFORCE class method) (agilerl.algorithms.sft.SFT class method) (agilerl.algorithms.td3.TD3 class method) (agilerl.components.data.Transition method) (agilerl.utils.cache.Cache method) load_() (agilerl.components.data.Transition method) load_checkpoint() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ilql.ILQL method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.wrappers.agent.AgentWrapper method) load_credentials() (in module agilerl.arena.auth) load_memmap() (agilerl.components.data.Transition method) load_minari_dataset() (in module agilerl.utils.minari_utils) load_state_dict() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method) (agilerl.components.data.Transition method) load_weights() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) local_step (agilerl.population.Population property) LocalTrainer (class in agilerl.training.trainer) log() (agilerl.metrics.AgentMetrics method) (agilerl.metrics.BaseMetrics method) (agilerl.metrics.MultiAgentMetrics method) (agilerl.utils.log_utils.DistributeCombineLogs method) log_histogram() (agilerl.metrics.AgentMetrics method) (agilerl.metrics.BaseMetrics method) (agilerl.metrics.MultiAgentMetrics method) log_prob() (agilerl.networks.actors.EvolvableDistribution method) LogEvent (class in agilerl.arena.stream) Logger (class in agilerl.logger) login() (agilerl.arena.client.ArenaClient method) logout() (agilerl.arena.client.ArenaClient method) LoraConfigDict (class in agilerl.models.networks) LstmSpec (class in agilerl.models.networks) M MADDPG (class in agilerl.algorithms.maddpg) make_dataset_env() (agilerl.models.env.LLMEnvSpec method) make_env() (agilerl.models.env.BanditEnvSpec method) (agilerl.models.env.GymEnvSpec method) (agilerl.models.env.PzEnvSpec method) make_multi_agent_vect_envs() (in module agilerl.utils.utils) make_rollout_env_factory() (agilerl.models.env.LLMEnvSpec method) make_safe_deepcopies() (in module agilerl.utils.algo_utils) make_single_env() (agilerl.models.env.GymEnvSpec method) (agilerl.models.env.PzEnvSpec method) make_skill_vect_envs() (in module agilerl.utils.utils) make_vect_envs() (in module agilerl.utils.utils) MakeEvolvable (class in agilerl.wrappers.make_evolvable) map_pytree() (in module agilerl.utils.torch_utils) MATD3 (class in agilerl.algorithms.matd3) maybe_add_batch_dim() (in module agilerl.utils.algo_utils) maybe_dense_stack() (agilerl.components.data.Transition method) memmap() (agilerl.components.data.Transition method) memmap_() (agilerl.components.data.Transition method) memmap_like() (agilerl.components.data.Transition method) memmap_refresh_() (agilerl.components.data.Transition method) MetricsReport (class in agilerl.population) min() (agilerl.components.segment_tree.MinSegmentTree method) minari_to_agile_buffer() (in module agilerl.utils.minari_utils) minari_to_agile_dataset() (in module agilerl.utils.minari_utils) MinSegmentTree (class in agilerl.components.segment_tree) MLP (class in agilerl.modules.gpt) mlp_init_dict (agilerl.modules.multi_input.EvolvableMultiInput property) MlpSpec (class in agilerl.models.networks) model_config (agilerl.arena.inference.LLMCompletionResult attribute) (agilerl.arena.inference.LLMParams attribute) (agilerl.arena.inference.LLMResults attribute) (agilerl.arena.inference.PredictResult attribute) (agilerl.arena.inference.SessionDetail attribute) (agilerl.arena.inference.SessionInfo attribute) (agilerl.arena.inference.SessionMessage attribute) (agilerl.arena.inference.StatusResponse attribute) (agilerl.arena.models.TrainingManifest attribute) (agilerl.models.algo.AlgorithmSpec attribute) (agilerl.models.algo.LLMAlgorithmSpec attribute) (agilerl.models.algo.MultiAgentRLAlgorithmSpec attribute) (agilerl.models.algo.RLAlgorithmSpec attribute) (agilerl.models.env.BanditEnvSpec attribute) (agilerl.models.env.GymEnvSpec attribute) (agilerl.models.env.LLMEnvSpec attribute) (agilerl.models.env.OfflineEnvSpec attribute) (agilerl.models.env.PzEnvSpec attribute) (agilerl.models.hpo.MultiFrequencySelectionSpec attribute) (agilerl.models.hpo.MutationProbabilities attribute) (agilerl.models.hpo.MutationSpec attribute) (agilerl.models.hpo.TournamentSelectionSpec attribute) (agilerl.models.manifest.TrainingManifest attribute) (agilerl.models.networks.CnnSpec attribute) (agilerl.models.networks.ContinuousQNetworkSpec attribute) (agilerl.models.networks.DeterministicActorSpec attribute) (agilerl.models.networks.FinetuningNetworkSpec attribute) (agilerl.models.networks.LoraConfigDict attribute) (agilerl.models.networks.LstmSpec attribute) (agilerl.models.networks.MlpSpec attribute) (agilerl.models.networks.MultiInputSpec attribute) (agilerl.models.networks.NetworkSpec attribute) (agilerl.models.networks.QNetworkSpec attribute) (agilerl.models.networks.RainbowQNetworkSpec attribute) (agilerl.models.networks.SimbaSpec attribute) (agilerl.models.networks.StochasticActorSpec attribute) (agilerl.models.networks.ValueNetworkSpec attribute) (agilerl.models.training.ReplayBufferSpec attribute) (agilerl.models.training.TrainingSpec attribute) model_dump() (agilerl.models.networks.MlpSpec method) module agilerl.utils.probe_envs_llm module_checkpoint_dict() (in module agilerl.utils.algo_utils) module_checkpoint_multiagent() (in module agilerl.utils.algo_utils) module_checkpoint_single() (in module agilerl.utils.algo_utils) ModuleDict (class in agilerl.modules.base) MultiAgentMetrics (class in agilerl.metrics) MultiAgentRLAlgorithm (class in agilerl.algorithms.core.base) MultiAgentRLAlgorithmSpec (class in agilerl.models.algo) MultiFrequencySelection (class in agilerl.hpo.multi_frequency) MultiFrequencySelectionSpec (class in agilerl.models.hpo) MultiInputConditionalEnv (class in agilerl.utils.probe_envs_llm) MultiInputSpec (class in agilerl.models.networks) MultiPolicyEnv (class in agilerl.utils.probe_envs_ma) MultiPolicyImageEnv (class in agilerl.utils.probe_envs_ma) MultiStepReplayBuffer (class in agilerl.components.replay_buffer) mut (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) mutate() (agilerl.algorithms.core.registry.RLParameter method) mutation() (agilerl.hpo.mutation.Mutations method) (in module agilerl.modules.base) mutation_hook() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) MutationProbabilities (class in agilerl.models.hpo) MutationRegistry (class in agilerl.algorithms.core.registry) Mutations (class in agilerl.hpo.mutation) MutationSpec (class in agilerl.models.hpo) N name (agilerl.models.env.LLMEnvSpec property) NDJsonStream (class in agilerl.arena.stream) net_config (agilerl.modules.lstm.EvolvableLSTM property) (agilerl.modules.mlp.EvolvableMLP property) (agilerl.modules.multi_input.EvolvableMultiInput property) (agilerl.modules.resnet.EvolvableResNet property) (agilerl.modules.simba.EvolvableSimBa property) (agilerl.networks.actors.EvolvableDistribution property) NetworkGroup (class in agilerl.algorithms.core.registry) networks() (agilerl.algorithms.core.registry.MutationRegistry method) NetworkSpec (class in agilerl.models.networks) NeuralTS (class in agilerl.algorithms.neural_ts_bandit) NeuralUCB (class in agilerl.algorithms.neural_ucb_bandit) no_mutation() (agilerl.hpo.mutation.Mutations method) nonscalar_metrics (agilerl.metrics.BaseMetrics property) normalize_observation() (agilerl.wrappers.agent.RSNorm method) O obs_to_tensor() (in module agilerl.utils.algo_utils) ObsDependentRewardContActionsEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ObsDependentRewardContActionsImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ObsDependentRewardEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) ObsDependentRewardImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) observation_space (agilerl.vector.pz_vec_env.PettingZooVecEnv property) observation_space() (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) Observations (class in agilerl.vector.pz_async_vec_env) OfflineEnvSpec (class in agilerl.models.env) on_main_process() (agilerl.logger.Logger static method) open_inference_agent() (agilerl.arena.client.ArenaClient method) OpenEnvServer (class in agilerl.llm_envs.openenv_server) OpenEnvWrapper (class in agilerl.llm_envs.openenv_server) operate() (agilerl.components.segment_tree.MinSegmentTree method) (agilerl.components.segment_tree.SegmentTree method) (agilerl.components.segment_tree.SumSegmentTree method) optimizer_cls_names() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method) optimizer_networks (agilerl.algorithms.core.registry.MutationRegistry property) OptimizerWrapper (class in agilerl.algorithms.core.optimizer_wrapper) output_activation (agilerl.wrappers.make_evolvable.MakeEvolvable property) P parameter_mutation() (agilerl.hpo.mutation.Mutations method) parameter_norm() (in module agilerl.utils.torch_utils) parse_ndjson_line() (in module agilerl.arena.stream) PettingZooAutoResetParallelWrapper (class in agilerl.wrappers.pettingzoo_wrappers) PettingZooVecEnv (class in agilerl.vector.pz_vec_env) policy() (agilerl.algorithms.core.registry.MutationRegistry method) PolicyContActionsEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) PolicyContActionsImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) PolicyContActionsImageEnvSimple (class in agilerl.utils.probe_envs) PolicyEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) PolicyImageEnv (class in agilerl.utils.probe_envs) (class in agilerl.utils.probe_envs_ma) Population (class in agilerl.population) population() (agilerl.algorithms.cispo.CISPO class method) (agilerl.algorithms.core.base.MultiAgentRLAlgorithm class method) (agilerl.algorithms.core.base.RLAlgorithm class method) (agilerl.algorithms.cqn.CQN class method) (agilerl.algorithms.ddpg.DDPG class method) (agilerl.algorithms.dpo.DPO class method) (agilerl.algorithms.dqn.DQN class method) (agilerl.algorithms.dqn_rainbow.RainbowDQN class method) (agilerl.algorithms.grpo.GRPO class method) (agilerl.algorithms.gspo.GSPO class method) (agilerl.algorithms.ippo.IPPO class method) (agilerl.algorithms.maddpg.MADDPG class method) (agilerl.algorithms.matd3.MATD3 class method) (agilerl.algorithms.neural_ts_bandit.NeuralTS class method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB class method) (agilerl.algorithms.ppo.PPO class method) (agilerl.algorithms.ppo_llm.PPO class method) (agilerl.algorithms.reinforce_llm.REINFORCE class method) (agilerl.algorithms.sft.SFT class method) (agilerl.algorithms.td3.TD3 class method) PopulationMetrics (class in agilerl.population) PositionalEncoder (class in agilerl.modules.bert) PositionalEncoding (class in agilerl.modules.bert) (class in agilerl.modules.gpt) PPO (class in agilerl.algorithms.ppo) (class in agilerl.algorithms.ppo_llm) predict() (agilerl.arena.inference.Agent method) PredictResult (class in agilerl.arena.inference) prepare_env_upload() (in module agilerl.arena.utils) prepare_file_upload() (in module agilerl.arena.utils) prepare_sequence_tensors() (agilerl.components.rollout_buffer.RolloutBuffer method) preprocess_observation() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.core.base.RLAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (in module agilerl.utils.algo_utils) preserve_parameters() (agilerl.modules.base.EvolvableModule static method) preview_experiment_metrics_csv() (agilerl.arena.client.ArenaClient method) print_hyperparams() (in module agilerl.utils.utils) PrioritizedReplayBuffer (class in agilerl.components.replay_buffer) process_infos() (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) process_transition() (in module agilerl.vector.pz_async_vec_env) profile_environment() (agilerl.arena.client.ArenaClient method) PzEnvSpec (class in agilerl.models.env) Q QNetwork (class in agilerl.networks.q_networks) QNetworkSpec (class in agilerl.models.networks) R RainbowDQN (class in agilerl.algorithms.dqn_rainbow) RainbowQNetwork (class in agilerl.networks.q_networks) RainbowQNetworkSpec (class in agilerl.models.networks) recompile() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) recreate_encoder() (agilerl.networks.base.EvolvableNetwork method) recreate_network() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.bert.EvolvableBERT method) (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.modules.resnet.EvolvableResNet method) (agilerl.modules.simba.EvolvableSimBa method) (agilerl.networks.actors.DeterministicActor method) (agilerl.networks.actors.StochasticActor method) (agilerl.networks.base.EvolvableNetwork method) (agilerl.networks.q_networks.ContinuousQNetwork method) (agilerl.networks.q_networks.QNetwork method) (agilerl.networks.q_networks.RainbowQNetwork method) (agilerl.networks.value_networks.ValueNetwork method) (agilerl.wrappers.make_evolvable.MakeEvolvable method) recursive_check_module_attrs() (in module agilerl.utils.algo_utils) refresh_access_token() (agilerl.arena.auth.ArenaOAuth2 method) register() (agilerl.metrics.BaseMetrics method) register_group() (agilerl.algorithms.core.registry.MutationRegistry method) register_histogram() (agilerl.metrics.BaseMetrics method) register_hook() (agilerl.algorithms.core.registry.MutationRegistry method) register_mutation_hook() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.modules.base.EvolvableModule method) register_network_group() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) register_optimizer() (agilerl.algorithms.core.registry.MutationRegistry method) REINFORCE (class in agilerl.algorithms.reinforce_llm) reinit_optimizers() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) RemoteEnvClient (class in agilerl.llm_envs.openenv) remove_block() (agilerl.modules.resnet.EvolvableResNet method) (agilerl.modules.simba.EvolvableSimBa method) remove_channel() (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.resnet.EvolvableResNet method) remove_cnn_channel() (agilerl.wrappers.make_evolvable.MakeEvolvable method) remove_cnn_layer() (agilerl.wrappers.make_evolvable.MakeEvolvable method) remove_compile_prefix() (in module agilerl.utils.algo_utils) remove_decoder_layer() (agilerl.modules.bert.EvolvableBERT method) remove_encoder_layer() (agilerl.modules.bert.EvolvableBERT method) remove_latent_node() (agilerl.modules.multi_input.EvolvableMultiInput method) (agilerl.networks.base.EvolvableNetwork method) remove_layer() (agilerl.modules.cnn.EvolvableCNN method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) remove_mlp_layer() (agilerl.wrappers.make_evolvable.MakeEvolvable method) remove_mlp_node() (agilerl.wrappers.make_evolvable.MakeEvolvable method) remove_nested_files() (in module agilerl.utils.algo_utils) remove_node() (agilerl.modules.bert.EvolvableBERT method) (agilerl.modules.gpt.EvolvableGPT method) (agilerl.modules.lstm.EvolvableLSTM method) (agilerl.modules.mlp.EvolvableMLP method) (agilerl.modules.simba.EvolvableSimBa method) render() (agilerl.population.MetricsReport method) (agilerl.vector.dummy_vec_env.DummyVecEnv method) (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) ReplayBuffer (class in agilerl.components.replay_buffer) ReplayBufferSpec (class in agilerl.models.training) ReplayDataset (class in agilerl.components.data) report_metrics() (agilerl.population.Population method) rescale_action() (agilerl.networks.actors.DeterministicActor static method) rescale_output_action() (agilerl.networks.actors.DeterministicActor method) reset() (agilerl.components.rollout_buffer.RolloutBuffer method) (agilerl.utils.probe_envs_llm.ConditionalTargetEnv method) (agilerl.utils.probe_envs_llm.ConstantTargetEnv method) (agilerl.utils.probe_envs_llm.GridNavigationEnv method) (agilerl.utils.probe_envs_llm.MultiInputConditionalEnv method) (agilerl.vector.dummy_vec_env.DummyVecEnv method) (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) (agilerl.wrappers.learning.BanditEnv method) (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) reset_action_noise() (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.td3.TD3 method) reset_async() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) reset_logs() (agilerl.utils.log_utils.DistributeCombineLogs method) reset_noise() (agilerl.modules.base.EvolvableModule method) (agilerl.modules.cnn.EvolvableCNN method) reset_wait() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) reshape_from_space() (in module agilerl.utils.algo_utils) resolve_env() (in module agilerl.llm_envs.openenv_server) result (agilerl.arena.stream.NDJsonStream property) resume_experiment() (agilerl.arena.client.ArenaClient method) retrieve() (agilerl.components.segment_tree.SumSegmentTree method) retrieve_batch() (agilerl.components.segment_tree.SumSegmentTree method) revoke() (agilerl.arena.auth.ArenaOAuth2 method) rl_hyperparam_mutation() (agilerl.hpo.mutation.Mutations method) RLAlgorithm (class in agilerl.algorithms.core.base) RLAlgorithmSpec (class in agilerl.models.algo) RLParameter (class in agilerl.algorithms.core.registry) RolloutBuffer (class in agilerl.components.rollout_buffer) RolloutCollector (class in agilerl.llm_envs) RolloutHarness (class in agilerl.llm_envs) RSNorm (class in agilerl.wrappers.agent) run_selection_and_mutation() (in module agilerl.utils.utils) S sample() (agilerl.algorithms.core.registry.HyperparameterConfig method) (agilerl.components.replay_buffer.MultiStepReplayBuffer method) (agilerl.components.replay_buffer.PrioritizedReplayBuffer method) (agilerl.components.replay_buffer.ReplayBuffer method) sample_distributed() (agilerl.components.sampler.Sampler method) sample_eval_prompts() (in module agilerl.utils.llm_utils) sample_from_indices() (agilerl.components.replay_buffer.MultiStepReplayBuffer method) sample_mutation_method() (agilerl.modules.base.EvolvableModule method) sample_n_step() (agilerl.components.sampler.Sampler method) sample_per() (agilerl.components.sampler.Sampler method) sample_standard() (agilerl.components.sampler.Sampler method) Sampler (class in agilerl.components.sampler) save() (agilerl.components.data.Transition method) save_checkpoint() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ilql.ILQL method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) (agilerl.wrappers.agent.AgentWrapper method) save_llm_checkpoint() (in module agilerl.utils.utils) save_population_checkpoint() (in module agilerl.utils.utils) scalar_fitness() (in module agilerl.utils.population_utils) scale_action() (agilerl.networks.actors.StochasticActor method) scores (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) SegmentTree (class in agilerl.components.segment_tree) select() (agilerl.components.data.Transition method) (agilerl.hpo.multi_frequency.MultiFrequencySelection method) (agilerl.hpo.tournament.TournamentSelection method) select_adapter() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) SessionDetail (class in agilerl.arena.inference) SessionInfo (class in agilerl.arena.inference) SessionMessage (class in agilerl.arena.inference) set() (agilerl.components.data.Transition method) set_attr() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) set_default_project() (agilerl.arena.client.ArenaClient method) set_reference_policy() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) set_stream_handler() (agilerl.arena.client.ArenaClient method) set_training_mode() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) SFT (class in agilerl.algorithms.sft) share_encoder_parameters() (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.td3.TD3 method) (in module agilerl.utils.algo_utils) shared_network_names() (agilerl.algorithms.core.registry.NetworkGroup method) should_stop() (agilerl.population.Population method) show_mean_column (agilerl.population.MetricsReport property) shrink_preserve_parameters() (agilerl.modules.cnn.EvolvableCNN static method) SimbaSpec (class in agilerl.models.networks) single_action_space (agilerl.vector.pz_vec_env.PettingZooVecEnv property) single_observation_space (agilerl.vector.pz_vec_env.PettingZooVecEnv property) size (agilerl.components.replay_buffer.MultiStepReplayBuffer property) (agilerl.components.replay_buffer.PrioritizedReplayBuffer property) (agilerl.components.replay_buffer.ReplayBuffer property) (agilerl.population.Population property) size() (agilerl.components.rollout_buffer.RolloutBuffer method) Skill (class in agilerl.wrappers.learning) skill_reward() (agilerl.wrappers.learning.Skill method) soft_update() (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.ilql.ILQL method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.td3.TD3 method) spec_to_factory() (in module agilerl.llm_envs.env_specs) stack() (agilerl.components.data.Transition method) stack_and_pad_experiences() (in module agilerl.utils.algo_utils) stack_experiences() (agilerl.wrappers.agent.AsyncAgentsWrapper method) (in module agilerl.utils.algo_utils) state (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper property) state_dict() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method) (agilerl.components.data.Transition method) status() (agilerl.arena.inference.Agent method) StatusEvent (class in agilerl.arena.stream) StatusResponse (class in agilerl.arena.inference) StdOutLogger (class in agilerl.logger) step() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method) (agilerl.utils.probe_envs_llm.ConditionalTargetEnv method) (agilerl.utils.probe_envs_llm.ConstantTargetEnv method) (agilerl.utils.probe_envs_llm.GridNavigationEnv method) (agilerl.utils.probe_envs_llm.MultiInputConditionalEnv method) (agilerl.vector.dummy_vec_env.DummyVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) (agilerl.wrappers.learning.BanditEnv method) (agilerl.wrappers.learning.Skill method) (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper method) step_async() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) step_wait() (agilerl.vector.pz_async_vec_env.AsyncPettingZooVecEnv method) (agilerl.vector.pz_vec_env.PettingZooVecEnv method) steps (agilerl.algorithms.cispo.CISPO property) (agilerl.algorithms.core.base.EvolvableAlgorithm property) (agilerl.algorithms.cqn.CQN property) (agilerl.algorithms.ddpg.DDPG property) (agilerl.algorithms.dpo.DPO property) (agilerl.algorithms.dqn.DQN property) (agilerl.algorithms.dqn_rainbow.RainbowDQN property) (agilerl.algorithms.grpo.GRPO property) (agilerl.algorithms.gspo.GSPO property) (agilerl.algorithms.ippo.IPPO property) (agilerl.algorithms.maddpg.MADDPG property) (agilerl.algorithms.matd3.MATD3 property) (agilerl.algorithms.neural_ts_bandit.NeuralTS property) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB property) (agilerl.algorithms.ppo.PPO property) (agilerl.algorithms.ppo_llm.PPO property) (agilerl.algorithms.reinforce_llm.REINFORCE property) (agilerl.algorithms.sft.SFT property) (agilerl.algorithms.td3.TD3 property) StochasticActor (class in agilerl.networks.actors) StochasticActorSpec (class in agilerl.models.networks) stop_experiment() (agilerl.arena.client.ArenaClient method) storage (agilerl.components.replay_buffer.MultiStepReplayBuffer property) (agilerl.components.replay_buffer.PrioritizedReplayBuffer property) (agilerl.components.replay_buffer.ReplayBuffer property) StreamRichRenderer (class in agilerl.arena.output) strip_from_beginning() (in module agilerl.utils.ilql_utils) strip_from_end() (in module agilerl.utils.ilql_utils) submit_experiment() (agilerl.arena.client.ArenaClient method) sum() (agilerl.components.segment_tree.SumSegmentTree method) sum_shared_rewards() (agilerl.algorithms.core.base.MultiAgentRLAlgorithm method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) SumSegmentTree (class in agilerl.components.segment_tree) T TaskAssigner (class in agilerl.llm_envs) TD3 (class in agilerl.algorithms.td3) TensorboardLogger (class in agilerl.logger) tensordict_collate_fn() (agilerl.components.sampler.Sampler static method) test() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) TextAction (class in agilerl.llm_envs.openenv_server) TextObservation (class in agilerl.llm_envs.openenv_server) to() (in module agilerl.utils.torch_utils) to_arena_manifest() (agilerl.models.manifest.TrainingManifest class method) to_bin() (in module agilerl.utils.ilql_utils) to_decorator() (in module agilerl.utils.torch_utils) to_device() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) to_dict() (agilerl.population.MetricsReport method) (agilerl.population.PopulationMetrics method) to_nonscalar_dict() (agilerl.population.MetricsReport method) to_tensordict() (agilerl.components.data.Transition method) (in module agilerl.components.data) to_torch_tensor() (in module agilerl.components.data) TokenEmbedding (class in agilerl.modules.bert) (class in agilerl.modules.gpt) torch_modules() (agilerl.modules.base.EvolvableModule method) tournament_selection (agilerl.arena.models.TrainingManifest property) (agilerl.models.manifest.TrainingManifest property) tournament_selection_and_mutation() (in module agilerl.utils.utils) TournamentSelection (class in agilerl.hpo.tournament) TournamentSelectionSpec (class in agilerl.models.hpo) train() (agilerl.training.trainer.ArenaTrainer method) (agilerl.training.trainer.LocalTrainer method) (agilerl.training.trainer.Trainer method) train_llm_dataset() (in module agilerl.training.llm) train_llm_rollout() (in module agilerl.training.llm) train_multi_agent_off_policy() (in module agilerl.training.train_multi_agent_off_policy) train_multi_agent_on_policy() (in module agilerl.training.train_multi_agent_on_policy) train_off_policy() (in module agilerl.training.train_off_policy) train_offline() (in module agilerl.training.train_offline) train_on_policy() (in module agilerl.training.train_on_policy) train_rows() (agilerl.population.MetricsReport method) Trainer (class in agilerl.training.trainer) training (agilerl.wrappers.agent.AgentWrapper property) TrainingManifest (class in agilerl.arena.models) (class in agilerl.models.manifest) TrainingSpec (class in agilerl.models.training) Transition (class in agilerl.components.data) tuple_to_dict_obs() (in module agilerl.utils.evolvable_networks) tuple_to_dict_space() (in module agilerl.utils.evolvable_networks) U unbind() (agilerl.components.data.Transition method) unrolled_eval_networks() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) unwrap_models() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) unwrapped (agilerl.vector.pz_vec_env.PettingZooVecEnv property) (agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper property) update() (agilerl.algorithms.dqn.DQN method) (agilerl.population.Population method) (agilerl.utils.cache.Cache method) update_batch() (agilerl.components.segment_tree.MinSegmentTree method) (agilerl.components.segment_tree.SegmentTree method) (agilerl.components.segment_tree.SumSegmentTree method) update_lr() (agilerl.algorithms.cispo.CISPO static method) (agilerl.algorithms.dpo.DPO static method) (agilerl.algorithms.grpo.GRPO static method) (agilerl.algorithms.gspo.GSPO static method) (agilerl.algorithms.ppo_llm.PPO static method) (agilerl.algorithms.reinforce_llm.REINFORCE static method) (agilerl.algorithms.sft.SFT static method) update_priorities() (agilerl.components.replay_buffer.PrioritizedReplayBuffer method) update_statistics() (agilerl.wrappers.agent.RSNorm method) use_adapter() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) V validate_environment() (agilerl.arena.client.ArenaClient method) ValueNetwork (class in agilerl.networks.value_networks) ValueNetworkSpec (class in agilerl.models.networks) values() (agilerl.modules.base.ModuleDict method) (agilerl.utils.cache.Cache method) vectorize_experiences_by_agent() (in module agilerl.utils.algo_utils) W WandbLogger (class in agilerl.logger) wrap_models() (agilerl.algorithms.cispo.CISPO method) (agilerl.algorithms.core.base.EvolvableAlgorithm method) (agilerl.algorithms.cqn.CQN method) (agilerl.algorithms.ddpg.DDPG method) (agilerl.algorithms.dpo.DPO method) (agilerl.algorithms.dqn.DQN method) (agilerl.algorithms.dqn_rainbow.RainbowDQN method) (agilerl.algorithms.grpo.GRPO method) (agilerl.algorithms.gspo.GSPO method) (agilerl.algorithms.ippo.IPPO method) (agilerl.algorithms.maddpg.MADDPG method) (agilerl.algorithms.matd3.MATD3 method) (agilerl.algorithms.neural_ts_bandit.NeuralTS method) (agilerl.algorithms.neural_ucb_bandit.NeuralUCB method) (agilerl.algorithms.ppo.PPO method) (agilerl.algorithms.ppo_llm.PPO method) (agilerl.algorithms.reinforce_llm.REINFORCE method) (agilerl.algorithms.sft.SFT method) (agilerl.algorithms.td3.TD3 method) write() (agilerl.logger.CSVLogger method) (agilerl.logger.Logger method) (agilerl.logger.StdOutLogger method) (agilerl.logger.TensorboardLogger method) (agilerl.logger.WandbLogger method) write_to_shared_memory() (in module agilerl.vector.pz_async_vec_env) Z zero_grad() (agilerl.algorithms.core.optimizer_wrapper.OptimizerWrapper method)