General Utils¶
- agilerl.utils.utils.makeVectEnvs(env_name, num_envs=1)¶
Returns async-vectorized gym environments.
- agilerl.utils.utils.makeMultiAgentVectEnvs(env, num_envs=1)¶
Returns async-vectorized PettingZoo parallel environments.
- Parameters:
env (pettingzoo.utils.env.ParallelEnv) – PettingZoo parallel environment object
num_envs (int, optional) – Number of vectorized environments, defaults to 1
- agilerl.utils.utils.makeSkillVectEnvs(env_name, skill, num_envs=1)¶
Returns async-vectorized gym environments.
- Parameters:
env_name (str) – Gym environment name
skill (agilerl.wrappers.learning.Skill) – Skill wrapper to apply to environment
num_envs (int, optional) – Number of vectorized environments, defaults to 1
- agilerl.utils.utils.initialPopulation(algo, state_dim, action_dim, one_hot, net_config, INIT_HP, actor_network=None, critic_network=None, population_size=1, device='cpu', accelerator=None)¶
Returns population of identical agents.
- Parameters:
algo (str) – RL algorithm
state_dim (int) – State observation dimension
action_dim (int) – Action dimension
one_hot (bool) – One-hot encoding
INIT_HP (dict) – Initial hyperparameters
actor_network (nn.Module, optional) – Custom actor network, defaults to None
critic_network (nn.Module, optional) – Custom critic network, defaults to None
population_size (int, optional) – Number of agents in population, defaults to 1
device (str, optional) – Device for accelerated computing, ‘cpu’ or ‘cuda’, defaults to ‘cpu’
accelerator (accelerate.Accelerator(), optional) – Accelerator for distributed computing, defaults to None
- agilerl.utils.utils.printHyperparams(pop)¶
Prints current hyperparameters of agents in a population and their fitnesses.