Offline Meta Reinforcement Learning on Contextual-DMC Walker-LS In-distribution
934.6Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCProtocol=Few-shot, Distribution=In-distribution2026.03 | 934.6 | |
| UNICORN-SUPProtocol=Few-shot, Distribution=In-distribution2026.03 | 914.2 | |
| CSROProtocol=Few-shot, Distribution=In-distribution2026.03 | 899.2 | |
| UNICORN-SSProtocol=Few-shot, Distribution=In-distribution2026.03 | 880.7 | |
| FOCALProtocol=Few-shot, Distribution=In-distribution2026.03 | 875 | |
| DORAProtocol=Few-shot, Distribution=In-distribution2026.03 | 862.5 |