Offline Reinforcement Learning on Walker2d Medium-Expert v2
103.87Average ScoreRLDP
Evaluation results
| Method | Links | |
|---|---|---|
| RLDPSetting=low-coverage2026.03 | 103.87 | |
| HILPSetting=low-coverage2026.03 | 93.72 | |
| PSMSetting=low-coverage2026.03 | 79.32 | |
| FBSetting=low-coverage2026.03 | 60.17 | |
| TRACERcorruption_type=random simultaneous corruptions2024.11 | 47 | |
| RIQLcorruption_type=random simultaneous corruptions2024.11 | 23.6 | |
| IQLcorruption_type=random simultaneous corruptions2024.11 | 20.6 |