Offline Reinforcement Learning on LunarLander Gym (1k)
97ReturnsERSAC-Ell-N
Evaluation results
| Method | Links | |
|---|---|---|
| ERSAC-Ell-NDS=1k, Tau aggregation=0.1, 0.5, 0.92026.04 | 97 | |
| ERSAC-Ell-EpiDS=1k2026.04 | 97 | |
| ERSAC-Ell-Epi*DS=1k2026.04 | 97 | |
| Behavior PolicyDS=1k2026.04 | 89 | |
| ERSAC-CH-NDS=1k2026.04 | 74 | |
| SAC-NDS=1k2026.04 | 69 |