Reinforcement Learning on Quadruped URLB (downstream)
720Jump ScoreAMPED
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| AMPED2025.06 | 720 | 494 | 906 | 890 | 3,010 | |
| APT2025.06 | 720 | 468 | 821 | 758 | 2,767 | |
| AMPED2025.06 | 699 | 493 | 816 | 816 | 2,824 | |
| BeCL2025.06 | 668 | 394 | 640 | 635 | 2,337 | |
| RND2025.06 | 643 | 435 | 839 | 571 | 2,488 | |
| ComSD2025.06 | 607 | 336 | 684 | 396 | 2,023 | |
| CIC2025.06 | 580 | 442 | 693 | 630 | 2,345 | |
| DIAYN2025.06 | 555 | 398 | 644 | 404 | 2,001 | |
| CeSD2025.06 | 529 | 390 | 853 | 562 | 2,334 | |
| DDPG2025.06 | 337 | 251 | 511 | 209 | 1,308 | |
| Discrete Metraskill_variable=categorical2025.06 | 218 | 144 | 333 | 153 | 849 | |
| Continuous Metraskill_variable=Gaussian distribution2025.06 | 183 | 127 | 240 | 160 | 710 |