Offline Meta Reinforcement Learning on Cheetah-LS (out-of-distribution)
865.5Average ReturnSPC
Evaluation Results
| Method | Links | |
|---|---|---|
| SPCZero-shot=true2026.03 | 865.5 | |
| FOCALZero-shot=true2026.03 | 826.6 | |
| CSROZero-shot=true2026.03 | 813.9 | |
| UNICORN-SSZero-shot=true2026.03 | 806.1 | |
| UNICORN-SUPZero-shot=true2026.03 | 795.8 | |
| DORAZero-shot=true2026.03 | 785.8 |