Offline Reinforcement Learning on OGBench scene
59Average Task SuccessIQN
Evaluation results
| Method | Links | |
|---|---|---|
| IQNPolicy Type=Gaussian Policies2026.05 | 59 | |
| FlowIQN-RPolicy Type=Flow Policies2026.05 | 59 | |
| FQLPolicy Type=Gaussian Policies2026.05 | 57 | |
| floqPolicy Type=Flow Policies2026.05 | 57 | |
| Value FlowsPolicy Type=Flow Policies2026.05 | 57 | |
| FlowIQN-FQLPolicy Type=Flow Policies2026.05 | 56 | |
| CODACPolicy Type=Gaussian Policies2026.05 | 55 | |
| ReBRACPolicy Type=Gaussian Policies2026.05 | 41 | |
| BCPolicy Type=Gaussian Policies2026.05 | 5 |