Zero-shot Reinforcement Learning on ExORL RND Walker environment v1 (test)
644FlipDoDont
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DoDontMode=Zero-shot, Seeds=42024.06 | 644 | 436 | 894 | 872 | — | |
| HILPMode=Zero-shot, Seeds=42024.06 | 563 | 401 | 800 | 855 | — | |
| FBMode=Zero-shot, Seeds=42024.06 | 548 | 409 | 866 | 811 | — | |
| FDMMode=Zero-shot, Seeds=42024.06 | 415 | 295 | 821 | 476 | — | |
| SRCPSetting=Zero-shot2026.04 | 369 | 204 | 752 | 486 | 453 | |
| FDMSetting=Zero-shot2026.04 | 251 | 195 | 697 | 459 | 401 | |
| AESetting=Zero-shot2026.04 | 224 | 127 | 614 | 301 | 317 | |
| HILPSetting=Zero-shot2026.04 | 154 | 112 | 424 | 260 | 238 | |
| CLSetting=Zero-shot2026.04 | 83 | 46 | 255 | 72 | 114 | |
| LAPSetting=Zero-shot2026.04 | 71 | 60 | 343 | 87 | 140 | |
| FBSetting=Zero-shot2026.04 | 63 | 61 | 234 | 100 | 115 | |
| LRA-SRSetting=Zero-shot2026.04 | 62 | 52 | 246 | 88 | 112 |