Zero-shot Reinforcement Learning on ExORL RND (Quadruped environment) v1 (test)
758Jump SuccessFDM
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| FDMMode=Zero-shot, Seeds=42024.06 | 758 | 491 | 971 | 601 | — | |
| DoDontMode=Zero-shot, Seeds=42024.06 | 684 | 494 | 859 | 753 | — | |
| FBMode=Zero-shot, Seeds=42024.06 | 642 | 436 | 797 | 642 | — | |
| HILPMode=Zero-shot, Seeds=42024.06 | 556 | 393 | 810 | 542 | — | |
| SRCPSetting=Zero-shot2026.04 | 374 | 265 | 514 | 268 | 355 | |
| LRA-SRSetting=Zero-shot2026.04 | 272 | 192 | 390 | 208 | 266 | |
| HILPSetting=Zero-shot2026.04 | 239 | 169 | 344 | 174 | 232 | |
| AESetting=Zero-shot2026.04 | 238 | 167 | 351 | 180 | 234 | |
| FDMSetting=Zero-shot2026.04 | 237 | 168 | 355 | 164 | 231 | |
| FBSetting=Zero-shot2026.04 | 190 | 131 | 270 | 141 | 183 | |
| LAPSetting=Zero-shot2026.04 | 173 | 136 | 265 | 143 | 179 | |
| CLSetting=Zero-shot2026.04 | 77 | 53 | 105 | 51 | 72 |