OakEmu-RL v0.1.0

Appearance

RewardShapingOutput ​

python
RewardShapingOutput(reward: float, metadata: dict[str, int | float] = dict()) -> None

One reward-shaper output for a single step.

Source

Values ​

metadata ​

python
metadata: dict[str, int | float] = field(default_factory=dict)

Source

reward ​

python
reward: float

Source