Offline Reinforcement Learning on Machine Replacement tabular
97Cumulative ReturnsSAC-N
Evaluation results
| Method | Links | |
|---|---|---|
| SAC-NDS=100x2026.04 | 97 | |
| SAC-NDS=1000x2026.04 | 97 | |
| CH-NDS=1000x2026.04 | 97 | |
| Ell-NDS=1000x2026.04 | 97 | |
| Ell 0.9-NDS=1000x2026.04 | 97 | |
| CH-NDS=100x2026.04 | 96 | |
| Ell 0.9-NDS=100x2026.04 | 95 | |
| Ell-NDS=100x2026.04 | 94 | |
| Beh. PolicyDS=10x2026.04 | 93 | |
| Beh. PolicyDS=100x2026.04 | 93 | |
| Beh. PolicyDS=1000x2026.04 | 93 | |
| Ell 0.9-NDS=10x2026.04 | 90 | |
| Ell-NDS=10x2026.04 | 89 | |
| CH-NDS=10x2026.04 | 86 | |
| SAC-NDS=10x2026.04 | 84 |