General Utils

agilerl.utils.utils.make_vect_envs(env_name: str | None = None, num_envs=1, *, make_env: Callable | None = None, should_async_vector: bool = True, **env_kwargs)

Returns async-vectorized gym environments.

Parameters:

  • env_name (str) – Gym environment name

  • num_envs (int, optional) – Number of vectorized environments, defaults to 1

  • make_env (Callable, optional) – Function that creates a gym environment, defaults use gym.make(env_name)

  • should_async_vector (bool, optional) – Whether to asynchronous vectorized environments, defaults to True

agilerl.utils.utils.make_multi_agent_vect_envs(env, num_envs=1, **env_kwargs)

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.make_skill_vect_envs(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.create_population(algo, state_dim, action_dim, one_hot, net_config, INIT_HP, actor_network=None, critic_network=None, population_size=1, num_envs=1, device='cpu', accelerator=None, torch_compiler=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

  • net_config (dict or None) – Network configuration

  • 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

  • num_envs (int, optional) – Number of vectorized environments, 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

  • torch_compiler

agilerl.utils.utils.print_hyperparams(pop)

Prints current hyperparameters of agents in a population and their fitnesses.

Parameters:

pop (list[object]) – Population of agents

agilerl.utils.utils.plot_population_score(pop)

Plots the fitness scores of agents in a population.

Parameters:

pop (list[object]) – Population of agents