Offline Reinforcement Learning on walker2d medium v2
92.7Normalized ScoreReBRAC
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| ReBRACCategory=Non-diffusion, Delay=No delay2026.03 | 92.7 | — | — | — | — | — | — | — | |
| DQL*Category=Diffusion Policies, Delay=No delay2026.03 | 91.2 | — | — | — | — | — | — | — | |
| DQLCategory=Diffusion Policies, Delay=No delay2026.03 | 87 | — | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=42026.03 | 84.8 | — | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=02026.03 | 84.4 | — | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=82026.03 | 84.1 | — | — | — | — | — | — | — | |
| RLDPSetting=low-coverage2026.03 | 83.83 | — | — | — | — | — | — | — | |
| DVCategory=Diffusion Planners, Delay=No delay2026.03 | 82.8 | — | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=162026.03 | 80.3 | — | — | — | — | — | — | — | |
| DiffuserCategory=Diffusion Planners, Delay=No delay2026.03 | 79.6 | — | — | — | — | — | — | — | |
| CQLCategory=Non-diffusion, Delay=No delay2026.03 | 79.2 | — | — | — | — | — | — | — | |
| HILPSetting=low-coverage2026.03 | 56.34 | — | — | — | — | — | — | — | |
| PSMSetting=low-coverage2026.03 | 55.7 | — | — | — | — | — | — | — | |
| FBSetting=low-coverage2026.03 | 43.72 | — | — | — | — | — | — | — | |
| BCCategory=Non-diffusion, Delay=No delay2026.03 | 6.6 | — | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=42026.03 | -0.1 | — | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=82026.03 | -0.1 | — | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=162026.03 | -0.1 | — | — | — | — | — | — | — | |
| EDAC2022.06 | — | 95.1 | 68.3 | 37.2 | 62.1 | 35.9 | 59.7 | — | |
| EDAC2022.06 | — | 95.1 | 52.9 | 18.7 | 45.7 | 18.8 | 46.2 | — | |
| LRTMode=lrt2025.10 | — | — | — | — | — | — | 568 | 10.79 | |
| LRT+QMode=lrt+q2025.10 | — | — | — | — | — | — | 2,448 | 4.94 | |
| QMode=q2025.10 | — | — | — | — | — | — | 2,282 | 5.28 | |
| RORL2022.06 | — | 94.1 | 91 | 56.9 | 71 | 43.3 | 71.2 | — | |
| RORLEnsemble size K=102022.06 | — | 94.1 | 89.1 | 39.1 | 61.8 | 26.7 | 62.2 | — | |
| SAC-10Ensemble size=102022.06 | — | 48.2 | 37 | 23 | 29.2 | 18.5 | 31.2 | — | |
| SAC-10Ensemble size K=102022.06 | — | 47.7 | 30.1 | 13.8 | 21.3 | 10.7 | 24.7 | — |