Offline Meta Reinforcement Learning on MuJoCo Hopper-mass In-distribution
590.6Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 590.6 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 572.7 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 563.3 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 540.9 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 476.4 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 442.5 |