Offline Meta Reinforcement Learning on Contextual-DMC Walker-friction In-distribution
563.6Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 563.6 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 539.1 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 532.3 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 521.8 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 487.7 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 485.5 |