Offline Meta Reinforcement Learning on Hopper-mass (out-of-distribution)
583.4Average ReturnSPC
Evaluation Results
| Method | Links | |
|---|---|---|
| SPCZero-shot=true2026.03 | 583.4 | |
| UNICORN-SSZero-shot=true2026.03 | 550.7 | |
| FOCALZero-shot=true2026.03 | 547.3 | |
| CSROZero-shot=true2026.03 | 543.6 | |
| DORAZero-shot=true2026.03 | 534.2 | |
| UNICORN-SUPZero-shot=true2026.03 | 463.9 |