Offline Reinforcement Learning on D4RL HalfCheetah-Full-Replay
94.9Normalized ScorePSPO
Evaluation results
| Method | Links | |
|---|---|---|
| PSPOAveraged across=4 random seeds2026.05 | 94.9 | |
| PMDBNumber of random seeds=42026.03 | 90 | |
| PMDB2026.05 | 90 | |
| RAMBONumber of random seeds=42026.03 | 87 | |
| RAMBO2026.05 | 87 | |
| AMGNumber of random seeds=42026.03 | 86.3 | |
| ADM2026.05 | 86.3 | |
| EPQNumber of random seeds=42026.03 | 85.3 | |
| EPQ2026.05 | 85.3 | |
| RRPINumber of random seeds=42026.03 | 83.7 | |
| DMGNumber of random seeds=42026.03 | 79.9 | |
| DMG2026.05 | 79.9 | |
| CQLNumber of random seeds=42026.03 | 76.9 | |
| CQL2026.05 | 76.9 | |
| MOReLNumber of random seeds=42026.03 | 70.1 | |
| MOReL2026.05 | 70.1 |