OakEmu-RL v0.1.0

Appearance

PPOActorEnvironmentRuntime ​

Minimal per-environment state required by the PPO actor step processor.

Source

Methods ​

reset ​

python
reset(observation: np.ndarray | None, trajectory_session: ActiveTrajectorySession | None = None) -> None

Source

Values ​

episode_length ​

python
episode_length: int

Source

episode_reward ​

python
episode_reward: float

Source

previous_potential ​

python
previous_potential: float | None

Source

state ​

python
state: np.ndarray | None

Source

trajectory_session ​

python
trajectory_session: ActiveTrajectorySession

Source