BaseDistributedEnv

class maze.train.parallelization.distributed_env.distributed_env.BaseDistributedEnv(num_envs: int)

Abstract base class for distributed environments.

Param

num_envs: the number of distributed environments.

abstract reset()

Reset all the environments and return respective observations in env-aggregated form.

Returns

observations in env-aggregated form.

abstract seed(seed: int = None) → None

Sets the seed for this distributed env’s random number generator(s) and its contained parallel envs.

abstract step(actions: Iterable[Any]) → Tuple[Dict[str, numpy.ndarray], numpy.ndarray, numpy.ndarray, Iterable[Dict[Any, Any]]]

Step the environments with the given actions.

Parameters

actions – the list of actions for the respective envs.

Returns

observations, rewards, dones, information-dicts all in env-aggregated form.