Settings
Cyclopts dataclasses for Stable-Baselines3 training with Schola (PPO, SAC, checkpoints, resume).
| Name | Description |
|---|---|
| BaseSb3AlgorithmSettings | Shared rollout and optimizer settings for on-policy SB3 algorithms. |
| PPOTrainSettings | Dataclass for configuring the settings of the Proximal Policy Optimization (PPO) algorithm. |
| SACTrainSettings | Dataclass for configuring the settings of the Soft Actor-Critic (SAC) algorithm. |
| Sb3CheckpointSettings | SB3-specific checkpoint settings. |
| Sb3LoggingSettings | Dataclass for configuring logging settings for the training process. |
| Sb3NetworkArchitectureSettings | Network architecture settings for SB3 algorithms. |
| Sb3ResumeSettings | Dataclass for holding arguments related to resuming training from a saved state. |
| Sb3TrainingSettings | Top-level training run options for the SB3 launcher (mirrors RLlib’s TrainingSettings grouping). |
| Sb3TrainScriptSettings | Top level dataclass for configuring the script arguments used in the SB3 launcher. |