Module: tf_agents.environments.wrappers

Environment wrappers.

Wrappers in this module can be chained to change the overall behaviour of an environment in common ways.


class ActionClipWrapper: Wraps an environment and clips actions to spec before applying.

class ActionDiscretizeWrapper: Wraps an environment with continuous actions and discretizes them.

class ActionOffsetWrapper: Offsets actions to be zero-based.

class ActionRepeat: Repeates actions over n-steps while acummulating the received reward.

class ExtraDisabledActionsWrapper: Adds extra unavailable actions.

class FixedLength: Truncates long episodes and pads short episodes to have a fixed length.

class FlattenActionWrapper: Flattens the action.

class FlattenObservationsWrapper: Wraps an environment and flattens nested multi-dimensional observations.

class GoalReplayEnvWrapper: Adds a goal to the observation, used for HER (Hindsight Experience Replay).

class HistoryWrapper: Adds observation and action history to the environment's observations.

class ObservationFilterWrapper: Filters observations based on an array of indexes.

class OneHotActionWrapper: Converts discrete action to one_hot format.

class PerformanceProfiler: End episodes after specified number of steps.

class PyEnvironmentBaseWrapper: PyEnvironment wrapper forwards calls to the given environment.

class RunStats: Wrapper that accumulates run statistics as the environment iterates.

class TimeLimit: End episodes after specified number of steps.

absolute_import Instance of __future__._Feature
division Instance of __future__._Feature
print_function Instance of __future__._Feature