Offline Reinforcement Learning on risk-sensitive D4RL Hopper Medium
1,590CVaR 0.1 ReturnRS-Diffuser
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RS-Diffuser2026.06 | 1,590 | 1,732 | |
| UDAC2026.06 | 1,502 | 1,602 | |
| ORAAC2026.06 | 1,416 | 1,482 | |
| CQL2026.06 | 1,344 | 1,524 | |
| Diffusion-QL2026.06 | 981 | 1,001 | |
| CODAC2026.06 | 976 | 1,014 | |
| OWCPG2026.06 | -87 | 69 |