Offline Reinforcement Learning on CartPole 1k Gym
90ReturnsBehavior Policy
Evaluation Results
| Method | Links | |
|---|---|---|
| Behavior PolicyDS=1k2026.04 | 90 | |
| ERSAC-Ell-NDS=1k, Tau aggregation=0.1, 0.5, 0.92026.04 | 79 | |
| ERSAC-Ell-EpiDS=1k2026.04 | 79 | |
| ERSAC-Ell-Epi*DS=1k2026.04 | 77 | |
| SAC-NDS=1k2026.04 | 76 | |
| ERSAC-CH-NDS=1k2026.04 | 74 |