OakEmu-RL v0.1.0

Appearance

TesterEnvironmentState ​

python
TesterEnvironmentState(state: np.ndarray | None = None, episode_reward: float = 0.0, episode_length: int = 0) -> None

State tracked per-environment in the Tester.

Source

Methods ​

reset ​

python
reset(observation: np.ndarray | None) -> None

Reset the environment state for a new episode.

Parameters:

  • observation (ndarray | None) – The initial observation.

Source

Values ​

episode_length ​

python
episode_length: int = 0

Number of steps in the current episode.

Source

episode_reward ​

python
episode_reward: float = 0.0

Cumulative reward for the current episode.

Source

state ​

python
state: np.ndarray | None = field(default=None, repr=False)

Current state observation.

Source