Offline Reinforcement Learning on D4RL Walker-2D Medium (Risk-Sensitive)
1,493CVaR 0.1RS-Diffuser
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RS-Diffuser2026.06 | 1,493 | 1,588 | |
| UDAC2026.06 | 1,368 | 1,602 | |
| CQL2026.06 | 1,244 | 1,524 | |
| CODAC2026.06 | 1,159 | 1,537 | |
| ORAAC2026.06 | 663 | 1,134 | |
| Diffusion-QL2026.06 | 31 | 273 | |
| OWCPG2026.06 | -15 | 283 |