DiscretizeActionsWrapper¶
-
class
maze.core.wrappers.discretize_actions_wrapper.
DiscretizeActionsWrapper
(*args, **kwds)¶ - The DiscretizeActionsWrapper provides functionality for discretizing individual continuous actions into discrete
ones.
An example is given by having a continuous action called ‘action_up’ with space: gym.spaces.Box(shape=(5,), low=[-1,-1,-1,-1,-1], high=[1,1,1,1,1]
- discretization_config:
- action_up:
num_bins: 5 low: [-1, 0, 0.5, 0, 0] high: 1
Now the action space will be split where each of the 5 continuous values of the box spaces are split evenly within the ranges of (-1,1),(0,1),(0.5,1), (0,1), (0,1) respectively.
- Parameters
env – Environment/wrapper to wrap.
discretization_config – The action discretization configuration.
-
action
(action: Dict[str, numpy.ndarray]) → Dict[str, numpy.ndarray]¶ (overrides
ActionWrapper
)Implementation of
ActionWrapper
interface.
-
property
action_space
¶ (overrides
StructuredEnvSpacesMixin
)The currently active gym action space.
-
property
action_spaces_dict
¶ (overrides
StructuredEnvSpacesMixin
)A dictionary of gym action spaces, with policy IDs as keys.
-
clone_from
(env: maze.core.wrappers.discretize_actions_wrapper.DiscretizeActionsWrapper) → None¶ (overrides
SimulatedEnvMixin
)implementation of
SimulatedEnvMixin
.
-
reverse_action
(action: Dict[str, numpy.ndarray]) → Dict[str, numpy.ndarray]¶ (overrides
ActionWrapper
)Implementation of
ActionWrapper
interface.