Offline Meta Reinforcement Learning on MuJoCo Cheetah-speed In-distribution
751.2Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 751.2 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 586.4 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 576.3 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 554.3 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 547 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 515.7 |