Offline Reinforcement Learning on D4RL Hopper risk-sensitive Expert
1,475CVaR 0.1RS-Diffuser
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RS-Diffuser2026.06 | 1,475 | 1,623 | |
| UDAC2026.06 | 1,302 | 1,502 | |
| CQL2026.06 | 1,289 | 1,402 | |
| CODAC2026.06 | 990 | 1,398 | |
| ORAAC2026.06 | 980 | 1,385 | |
| OWCPG2026.06 | 720 | 898 | |
| Diffusion-QL2026.06 | 406 | 583 |