puzzle-3x3-task4 on OGBench
16Success RateFQL
Evaluation Results
| Method | Links | |
|---|---|---|
| FQLPolicy Type=Flow Policies, Evaluation Protocol=Offline RL2026.05 | 16 | |
| DFPPolicy Type=Ours, Evaluation Protocol=Offline RL2026.05 | 3 | |
| IQLPolicy Type=Gaussian Policies, Evaluation Protocol=Offline RL2026.05 | 2 | |
| ReBRACPolicy Type=Gaussian Policies, Evaluation Protocol=Offline RL2026.05 | 2 | |
| FBRACPolicy Type=Flow Policies, Evaluation Protocol=Offline RL2026.05 | 2 | |
| BCPolicy Type=Gaussian Policies, Evaluation Protocol=Offline RL2026.05 | 1 | |
| FAWACPolicy Type=Flow Policies, Evaluation Protocol=Offline RL2026.05 | 1 | |
| IDQLPolicy Type=Diffusion Policies, Evaluation Protocol=Offline RL2026.05 | 0 | |
| SRPOPolicy Type=Diffusion Policies, Evaluation Protocol=Offline RL2026.05 | 0 | |
| CACPolicy Type=Flow Policies, Evaluation Protocol=Offline RL2026.05 | 0 | |
| IFQLPolicy Type=Flow Policies, Evaluation Protocol=Offline RL2026.05 | 0 |