Offline Reinforcement Learning on hopper medium v2
102Normalized ScoreDQL*
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| DQL*Category=Diffusion Policies, Delay=No delay2026.03 | 102 | — | — | — | — | — | — | |
| ReBRACCategory=Non-diffusion, Delay=No delay2026.03 | 91.1 | — | — | — | — | — | — | |
| DQLCategory=Diffusion Policies, Delay=No delay2026.03 | 90.5 | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=162026.03 | 86.6 | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=02026.03 | 84.6 | — | — | — | — | — | — | |
| DVCategory=Diffusion Planners, Delay=No delay2026.03 | 83.6 | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=82026.03 | 83.5 | — | — | — | — | — | — | |
| SAIDCategory=Diffusion Planners, Delay=42026.03 | 82 | — | — | — | — | — | — | |
| DiffuserCategory=Diffusion Planners, Delay=No delay2026.03 | 74.3 | — | — | — | — | — | — | |
| CQLCategory=Non-diffusion, Delay=No delay2026.03 | 58 | — | — | — | — | — | — | |
| BCCategory=Non-diffusion, Delay=No delay2026.03 | 29 | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=42026.03 | 3.1 | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=82026.03 | 2 | — | — | — | — | — | — | |
| DQL+SACategory=Baseline w/ delay, Delay=162026.03 | 2 | — | — | — | — | — | — | |
| EDAC2022.06 | — | 7,220 | 6,970 | 4,550 | 38.3 | 23.7 | 4,990 | |
| EDAC2022.06 | — | 61.7 | 61.4 | 30.8 | 21.7 | 9.6 | 37 | |
| FBSetting=low-coverage2026.03 | — | — | — | — | — | — | 43.75 | |
| HILPSetting=low-coverage2026.03 | — | — | — | — | — | — | 52.19 | |
| PSMSetting=low-coverage2026.03 | — | — | — | — | — | — | 33.49 | |
| RLDPSetting=low-coverage2026.03 | — | — | — | — | — | — | 44.93 | |
| RORL2022.06 | — | 8,480 | 7,840 | 5,390 | 51.5 | 34.7 | 6,070 | |
| RORLEnsemble size K=102022.06 | — | 76 | 68 | 36.1 | 37.4 | 21.1 | 47.7 | |
| SAC-10Ensemble size=102022.06 | — | 79 | 82 | 89 | 0.88 | 1.36 | 95 | |
| SAC-10Ensemble size K=102022.06 | — | 0.8 | 0.84 | 0.93 | 0.91 | 1.67 | 1.03 |