OakEmu-RL v0.1.0

Appearance

ActorRuntimeState ​

python
ActorRuntimeState(steps: int, episode_totals: AgentEpisodeTotalsState, trajectory_state_dict: dict[str, Any] | None = None) -> None

Checkpoint-restorable runtime state shared by the DQN trainer and PPO actor.

Source

Values ​

episode_totals ​

python
episode_totals: AgentEpisodeTotalsState

Source

steps ​

python
steps: int

Source

trajectory_state_dict ​

python
trajectory_state_dict: dict[str, Any] | None = None

Source