Offline Reinforcement Learning on D4RL Adroit relocate-human
0.6Normalized ScoreFAC
Evaluation Results
| Method | Links | |
|---|---|---|
| FACPolicy Type=Flow, Seeds=82026.02 | 0.6 | |
| EPQPolicy Type=Gaussian, Seeds=82026.02 | 0.3 | |
| CQLPolicy Type=Gaussian, Seeds=82026.02 | 0.2 | |
| IQLPolicy Type=Gaussian, Seeds=82026.02 | 0.1 | |
| MCQPolicy Type=Gaussian, Seeds=82026.02 | 0.1 | |
| SAC-RNDPolicy Type=Gaussian, Seeds=82026.02 | 0 | |
| ReBRACPolicy Type=Gaussian, Seeds=82026.02 | 0 | |
| IDQLPolicy Type=Diffusion, Seeds=82026.02 | 0 | |
| SRPOPolicy Type=Diffusion, Seeds=82026.02 | 0 | |
| CACPolicy Type=Diffusion, Seeds=82026.02 | 0 | |
| FQLPolicy Type=Flow, Seeds=82026.02 | 0 | |
| TD3+BCPolicy Type=Gaussian, Seeds=82026.02 | -0.2 |