Offline Reinforcement Learning on OGBench scene-singletask 5 tasks
58Normalized ScoreDROL
Evaluation results
| Method | Links | |
|---|---|---|
| DROLPolicy Class=One-step Method, K-selection protocol=benchmark-specific2026.04 | 58 | |
| SORLPolicy Class=Multi-step / Iterative Policy2026.04 | 57 | |
| FQLPolicy Class=One-step Method2026.04 | 56 | |
| DROLPolicy Class=One-step Method, K=162026.04 | 54 | |
| DeFlowPolicy Class=Multi-step / Iterative Policy2026.04 | 51 | |
| FBRACPolicy Class=Multi-step / Iterative Policy2026.04 | 45 | |
| ReBRACPolicy Class=Gaussian Policy2026.04 | 41 | |
| FAWACPolicy Class=Multi-step / Iterative Policy2026.04 | 30 | |
| IFQLPolicy Class=Multi-step / Iterative Policy2026.04 | 30 | |
| IQLPolicy Class=Gaussian Policy2026.04 | 28 | |
| BCPolicy Class=Gaussian Policy2026.04 | 5 |