Splits an actions into separate ones.
An example is given by the LunarLanderContinuous-v2 env. Here we have a box action spaces with shape (2,) such that dimension 0 is the up/down action and dimension 1 is the left/right action. Now if we would like to split this action correspondingly we can wrap the env with the following config:
Now the actions as well as the action space is consists of two actions (action_up/action_side).
env – Environment/wrapper to wrap.
split_config – The action splitting configuration.
action(action: Dict[str, numpy.ndarray]) → Dict[str, numpy.ndarray]¶
A dictionary of gym action spaces, with policy IDs as keys.
clone_from(env: maze.core.wrappers.split_actions_wrapper.SplitActionsWrapper) → None¶