Environment Interfaces¶

This page contains the reference documentation for environment interfaces.

maze.core.env¶

Environment interfaces:

`BaseEnv`	Interface definition for reinforcement learning environments defining the minimum required functionality for being considered an environment.
`ActorID`	Identifies an actor in the environment.
`StructuredEnv`	Interface for environments with sub-step structure, which is generally enough to cover multi-step, hierarchical and multi-agent environments.
`CoreEnv`	Interface definition for core environments forming the basis for actual RL trainable environments.
`StructuredEnvSpacesMixin`	This interface complements the StructuredEnv by action and observation spaces.
`MazeEnv`	Base class for (gym style) environments wrapping a core environment and defining state and execution interfaces.
`RenderEnvMixin`	Interface for rendering functionality in environments (compatible with gym env).
`RecordableEnvMixin`	This interface provides a standard way of exposing internal MazeState and MazeAction objects for trajectory data recording.
`SerializableEnvMixin`	This interface provides a standard way of exposing environment components whose state should be serialized together with the environment state object when for example recording trajectory data.
`TimeEnvMixin`	This interface provides a standard way of exposing environment time to external components and wrappers.
`EventEnvMixin`	This interface provides a standard way of attaching environment events to the log statistics system.
`SimulatedEnvMixin`	Environment interface for simulated environments.

Interfaces for additional components:

`ObservationConversionInterface`	Interface specifying the conversion of abstract environment state to the gym-compatible observation.
`ActionConversionInterface`	Interface specifying the conversion of agent actions to actual environment MazeActions.
`MazeStateType`	Internal indicator of special typing constructs.
`MazeActionType`	Internal indicator of special typing constructs.
`RewardAggregatorInterface`	Event aggregation object for reward customization and shaping.
`EnvironmentContext`	This class keeps track of services that can be employed by all objects of the agent-environment loop.