Gym Wrappers¶
Additional Gym Wrappers to enhance Gym environments.
TimeFeatureWrapper¶
- class sb3_contrib.common.wrappers.TimeFeatureWrapper(env, max_steps=1000, test_mode=False)[source]¶
Add remaining, normalized time to observation space for fixed length episodes. See https://arxiv.org/abs/1712.00378 and https://github.com/aravindr93/mjrl/issues/13.
Note
Only
gym.spaces.Box
andgym.spaces.Dict
(gym.GoalEnv
) 1D observation spaces are supported for now.- Parameters
env (
Env
) – Gym env to wrap.max_steps (
int
) – Max number of steps of an episode if it is not wrapped in aTimeLimit
object.test_mode (
bool
) – In test mode, the time feature is constant, equal to zero. This allow to check that the agent did not overfit this feature, learning a deterministic pre-defined sequence of actions.