Offline Meta Reinforcement Learning on MuJoCo Cheetah-LS In-distribution
944.8Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 944.8 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 895.3 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 852.2 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 832 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 831.2 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 795.9 |