Offline Reinforcement Learning on RiverSwim tabular
100ReturnsEll-N
Evaluation results
| Method | Links | |
|---|---|---|
| Ell-NDS=1000x2026.04 | 100 | |
| Ell 0.9-NDS=1000x2026.04 | 100 | |
| SAC-NDS=1000x2026.04 | 99 | |
| CH-NDS=1000x2026.04 | 99 | |
| Ell 0.9-NDS=100x2026.04 | 98 | |
| CH-NDS=100x2026.04 | 97 | |
| Ell-NDS=100x2026.04 | 97 | |
| SAC-NDS=100x2026.04 | 96 | |
| Ell 0.9-NDS=10x2026.04 | 60 | |
| CH-NDS=10x2026.04 | 58 | |
| Ell-NDS=10x2026.04 | 55 | |
| SAC-NDS=10x2026.04 | 47 | |
| Beh. PolicyDS=10x2026.04 | 5 | |
| Beh. PolicyDS=100x2026.04 | 5 | |
| Beh. PolicyDS=1000x2026.04 | 5 |