Offline Meta Reinforcement Learning on Walker-friction (out-of-distribution)
484.6Average ReturnUNICORN-SS
Evaluation Results
| Method | Links | |
|---|---|---|
| UNICORN-SSZero-shot=true2026.03 | 484.6 | |
| CSROZero-shot=true2026.03 | 475.1 | |
| SPCZero-shot=true2026.03 | 474.1 | |
| FOCALZero-shot=true2026.03 | 473.7 | |
| DORAZero-shot=true2026.03 | 462.4 | |
| UNICORN-SUPZero-shot=true2026.03 | 435.2 |