OakEmu-RL v0.1.0

Appearance

RewardShapingResult ​

python
RewardShapingResult(base_extrinsic_reward: float, extrinsic_reward: float, intrinsic_reward: float, shaped_reward: float, metadata: dict[str, int | float] = dict()) -> None

The result of running a step through the reward-shaping pipeline.

Source

Values ​

base_extrinsic_reward ​

python
base_extrinsic_reward: float

Source

extrinsic_reward ​

python
extrinsic_reward: float

Source

intrinsic_reward ​

python
intrinsic_reward: float

Source

metadata ​

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

Source

shaped_reward ​

python
shaped_reward: float

Source