OakEmu-RL v0.1.0

Appearance

RewardShapingStep ​

python
RewardShapingStep(env_id: int, state: np.ndarray, action: int, reward: float, next_state: np.ndarray, terminated: bool, truncated: bool, data: dict[str, float], step: int) -> None

A single environment step passed through the reward-shaping pipeline.

Source

Values ​

action ​

python
action: int

Source

data ​

python
data: dict[str, float]

Source

env_id ​

python
env_id: int

Source

next_state ​

python
next_state: np.ndarray

Source

reward ​

python
reward: float

Source

state ​

python
state: np.ndarray

Source

step ​

python
step: int

Source

terminated ​

python
terminated: bool

Source

truncated ​

python
truncated: bool

Source