Offline Meta Reinforcement Learning on Cheetah-speed out-of-distribution
756Average ReturnSPC
Evaluation Results
| Method | Links | |
|---|---|---|
| SPCZero-shot=true2026.03 | 756 | |
| FOCALZero-shot=true2026.03 | 607.8 | |
| CSROZero-shot=true2026.03 | 603.5 | |
| UNICORN-SSZero-shot=true2026.03 | 598.8 | |
| DORAZero-shot=true2026.03 | 573 | |
| UNICORN-SUPZero-shot=true2026.03 | 554.8 |