Offline Meta Reinforcement Learning on Walker-LS (out-of-distribution)
788Average ReturnSPC
Evaluation results
| Method | Links | |
|---|---|---|
| SPCZero-shot=true2026.03 | 788 | |
| FOCALZero-shot=true2026.03 | 658 | |
| UNICORN-SSZero-shot=true2026.03 | 657.6 | |
| DORAZero-shot=true2026.03 | 650.9 | |
| UNICORN-SUPZero-shot=true2026.03 | 649.9 | |
| CSROZero-shot=true2026.03 | 611.5 |