Locomotion on Walker2D
1,023RewardPAWS (MLP)
Evaluation Results
| Method | Links | |
|---|---|---|
| PAWS (MLP)#Preferences=5002026.06 | 1,023 | |
| PAWS (Trans.)#Preferences=5002026.06 | 997 | |
| P-IQL#Preferences=5002026.06 | 947 | |
| Pref Trans.#Preferences=5002026.06 | 726 | |
| CPL+KL#Preferences=5002026.06 | 476 | |
| CPL#Preferences=5002026.06 | 446 | |
| BC#Preferences=5002026.06 | 266 | |
| IPL#Preferences=5002026.06 | 251 | |
| PAWS (MLP)#Preferences=502026.06 | 235 | |
| PAWS (Trans.)#Preferences=502026.06 | 208 | |
| BC#Preferences=502026.06 | 167 | |
| IPL#Preferences=502026.06 | 160 | |
| Pref Trans.#Preferences=502026.06 | 150 | |
| CPL+KL#Preferences=502026.06 | 123 | |
| CPL#Preferences=502026.06 | 119 | |
| P-IQL#Preferences=502026.06 | 116 |