RewardScalingWrapper¶
-
class
maze.core.wrappers.reward_scaling_wrapper.
RewardScalingWrapper
(*args, **kwds)¶ Scales original step reward by a multiplicative scaling factor.
- Parameters
env – The underlying environment.
scale – Multiplicative reward scaling factor.
-
clone_from
(env: maze.core.wrappers.reward_scaling_wrapper.RewardScalingWrapper) → None¶ (overrides
SimulatedEnvMixin
)implementation of
SimulatedEnvMixin
.
-
reward
(reward: float) → float¶ (overrides
RewardWrapper
)Scales the original reward.
- param reward
The original reward.
- return
The scaled reward.