Offline Reinforcement Learning on D4RL Walker-2D risk-sensitive Expert
1,406CVaR 0.1RS-Diffuser
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RS-Diffuser2026.06 | 1,406 | 2,204 | |
| UDAC2026.06 | 1,398 | 2,198 | |
| CQL2026.06 | 1,301 | 2,018 | |
| CODAC2026.06 | 1,298 | 2,102 | |
| ORAAC2026.06 | 1,172 | 2,006 | |
| Diffusion-QL2026.06 | 621 | 1,202 | |
| OWCPG2026.06 | 362 | 1,372 |