Reinforcement Learning on Pendulum v1
-58.557RewardSAC-AdaGamma
Evaluation results
| Method | Links | |
|---|---|---|
| SAC-AdaGammaAdaptive-gamma=True2026.05 | -58.557 | |
| SACAdaptive-gamma=False2026.05 | -64.832 | |
| PPO-AdaGammaAdaptive-gamma=True2026.05 | -198.12 | |
| PPOAdaptive-gamma=False2026.05 | -212.27 |