Offline Reinforcement Learning on D4RL Half-Cheetah risk-sensitive Expert
793CVaR (0.1)
RS-Diffuser
Updated 27d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 793 | 1,409 | |
2026.06 | 732 | 1,352 | |
2026.06 | 687 | 1,255 | |
2026.06 | 595 | 1,180 | |
2026.06 | 542 | 728 | |
2026.06 | 248 | 905 | |
2026.06 | -207 | -75 |