Offline Reinforcement Learning on OGBench cube-triple-play
14Success RateValue Flows
Evaluation results
| Method | Links | |
|---|---|---|
| Value FlowsPolicy Type=Flow Policies2025.10 | 14 | |
| IQNPolicy Type=Flow Policies2025.10 | 6 | |
| FQLPolicy Type=Flow Policies2025.10 | 4 | |
| CODACPolicy Type=Flow Policies2025.10 | 2 | |
| IQLPolicy Type=Gaussian Policies2025.10 | 1 | |
| BCPolicy Type=Gaussian Policies2025.10 | 0 | |
| ReBRACPolicy Type=Gaussian Policies2025.10 | 0 | |
| FBRACPolicy Type=Flow Policies2025.10 | 0 | |
| IFQLPolicy Type=Flow Policies2025.10 | 0 | |
| C51Policy Type=Flow Policies2025.10 | 0 |