Offline Reinforcement Learning on D4RL Walker-2D risk-sensitive Mixed
531CVaR 0.1RS-Diffuser
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RS-Diffuser2026.06 | 531 | 377 | |
| UDAC2026.06 | 498 | 299 | |
| CODAC2026.06 | 450 | 261 | |
| Diffusion-QL2026.06 | 302 | 102 | |
| ORAAC2026.06 | 222 | -70 | |
| OWCPG2026.06 | 201 | -77 | |
| CQL2026.06 | 74 | -64 |