View source on GitHub |
Environment wrappers.
Wrappers in this module can be chained to change the overall behaviour of an environment in common ways.
Classes
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.
Other Members | |
---|---|
absolute_import |
Instance of __future__._Feature
|
division |
Instance of __future__._Feature
|
print_function |
Instance of __future__._Feature
|