Offline Meta Reinforcement Learning on Finger-speed (out-of-distribution)
948.1Average ReturnSPC
Evaluation Results
| Method | Links | |
|---|---|---|
| SPCZero-shot=true2026.03 | 948.1 | |
| CSROZero-shot=true2026.03 | 822.8 | |
| FOCALZero-shot=true2026.03 | 771.3 | |
| UNICORN-SSZero-shot=true2026.03 | 709.6 | |
| UNICORN-SUPZero-shot=true2026.03 | 675.3 | |
| DORAZero-shot=true2026.03 | 532.9 |