Offline Reinforcement Learning on LunarLander Gym (10k)
102ReturnsERSAC-Ell-Epi*
Evaluation results
| Method | Links | |
|---|---|---|
| ERSAC-Ell-Epi*DS=10k2026.04 | 102 | |
| ERSAC-Ell-NDS=10k, Tau aggregation=0.1, 0.5, 0.92026.04 | 101 | |
| ERSAC-Ell-EpiDS=10k2026.04 | 100 | |
| ERSAC-CH-NDS=10k2026.04 | 99 | |
| SAC-NDS=10k2026.04 | 93 | |
| Behavior PolicyDS=10k2026.04 | 89 |