Offline Reinforcement Learning on DeepMind Control Suite Quadruped (test)
854.5Stand ScoreLaplace
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| LaplaceSetting=Zero-shot offline RL2026.03 | 854.5 | 412.98 | 494.56 | 642.84 | |
| PSMSetting=Zero-shot offline RL2026.03 | 842.86 | 431.77 | 603.97 | 596.37 | |
| RLDPSetting=Zero-shot offline RL2026.03 | 794.94 | 457.41 | 465.4 | 733.32 | |
| FBSetting=Zero-shot offline RL2026.03 | 740.05 | 386.67 | 566.57 | 581.28 | |
| HILPSetting=Zero-shot offline RL2026.03 | 409.54 | 205.44 | 218.54 | 325.51 |