Offline Meta Reinforcement Learning on MuJoCo Ant-dir In-distribution
863.1Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 863.1 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 812.9 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 804 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 798 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 596.5 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 429 |