class maze.core.env.base_env.BaseEnv

Interface definition for reinforcement learning environments defining the minimum required functionality for being considered an environment.

abstract close()None

Performs any necessary cleanup.

abstract reset() → Any

Resets the environment and returns the initial state.


the initial state after resetting.

abstract seed(seed: Any)None

Sets the seed for this environment.

Commonly an integer is sufficient to seed the random number generator(s), but more expressive env-specific seed structured are also supported.


seed: the seed integer initializing the random number generator or an env-specific seed structure.

abstract step(action: Any) → Tuple[Any, Any, bool, Dict[Any, Any]]

Environment step function.


action – the selected action to take.


state, reward, done, info