Offline Reinforcement Learning on DeepMind Control Suite Walker (test)
902.63Stand ScoreFB
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FBSetting=Zero-shot offline RL2026.03 | 902.63 | 392.76 | 877.1 | 206.22 | |
| RLDPSetting=Zero-shot offline RL2026.03 | 877.69 | 324.85 | 790.94 | 491.64 | |
| PSMSetting=Zero-shot offline RL2026.03 | 872.61 | 351.5 | 891.44 | 640.75 | |
| HILPSetting=Zero-shot offline RL2026.03 | 607.07 | 107.84 | 399.67 | 277.95 | |
| LaplaceSetting=Zero-shot offline RL2026.03 | 243.7 | 63.65 | 190.53 | 48.73 |