Reinforcement Learning on Jaco URLB (downstream)
148Reach Count BLBeCL
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| BeCL2025.06 | 148 | 140 | 123 | 116 | 527 | |
| AMPED2025.06 | 143 | 144 | 140 | 154 | 581 | |
| AMPED2025.06 | 139 | 140 | 130 | 146 | 555 | |
| CeSD2025.06 | 136 | 134 | 175 | 97 | 542 | |
| CIC2025.06 | 135 | 152 | 137 | 149 | 573 | |
| DDPG2025.06 | 133 | 115 | 101 | 87 | 436 | |
| ComSD2025.06 | 126 | 111 | 126 | 121 | 484 | |
| APT2025.06 | 120 | 126 | 124 | 113 | 483 | |
| RND2025.06 | 101 | 115 | 97 | 122 | 435 | |
| Continuous Metraskill_variable=Gaussian distribution2025.06 | 26 | 21 | 21 | 24 | 93 | |
| DIAYN2025.06 | 20 | 22 | 22 | 12 | 76 | |
| Discrete Metraskill_variable=categorical2025.06 | 14 | 11 | 9 | 5 | 39 |