Petting Zoo Wrapper¶

Parameters¶

class agilerl.wrappers.pettingzoo_wrappers.PettingZooAutoResetParallelWrapper(env: ParallelEnv[AgentID, ObsType, ActionType])¶

Wrapper to automatically reset the environment when all agents terminate or truncate.

Parameters:: env (ParallelEnv[AgentID, ObsType, ActionType]) – The environment to wrap

action_space(agent: AgentID) → spaces.Space¶

Return the action space for the given agent.

observation_space(agent: AgentID) → spaces.Space¶

Return the observation space for the given agent.

render() → None | ndarray | str | list¶

Render the environment.

reset(seed: int | None = None, options: dict | None = None) → tuple[dict[AgentID, ObsType], dict[AgentID, dict]]¶

Reset the environment and return the initial observations and info.

Parameters:

seed (int | None, optional) – Random seed, defaults to None
options (dict | None, optional) – Options dictionary, defaults to None

Returns:

Tuple of (observations, infos)

Return type:

tuple[dict[str, np.ndarray], dict[str, Any]]

property state: ndarray¶

Return the state of the environment.

step(actions: dict[AgentID, ActionType]) → tuple[dict[AgentID, ObsType], dict[AgentID, float], dict[AgentID, bool], dict[AgentID, bool], dict[AgentID, dict]]¶

Step the environment and return the observations, rewards, terminations, truncations, and info.

Parameters:: actions (dict[str, ActionType]) – Actions dictionary
Returns:: Tuple of (observations, rewards, terminations, truncations, infos)
Return type:: tuple[dict[str, np.ndarray], dict[str, float], dict[str, bool], dict[str, bool], dict[str, Any]]

property unwrapped: ParallelEnv¶

Return the unwrapped environment.