List your company

Offline Reinforcement Learning on walker2d medium v2

92.7Normalized ScoreReBRAC
-3.81221.24446.371.356Mar 2, 2026Mar 4, 2026Mar 6, 2026Mar 9, 2026Mar 11, 2026Mar 13, 2026Mar 16, 2026

Evaluation results

MethodLinks
ReBRACCategory=Non-diffusion, Delay=No delay2026.0392.7———————
DQL*Category=Diffusion Policies, Delay=No delay2026.0391.2———————
DQLCategory=Diffusion Policies, Delay=No delay2026.0387———————
SAIDCategory=Diffusion Planners, Delay=42026.0384.8———————
SAIDCategory=Diffusion Planners, Delay=02026.0384.4———————
SAIDCategory=Diffusion Planners, Delay=82026.0384.1———————
RLDPSetting=low-coverage2026.0383.83———————
DVCategory=Diffusion Planners, Delay=No delay2026.0382.8———————
SAIDCategory=Diffusion Planners, Delay=162026.0380.3———————
DiffuserCategory=Diffusion Planners, Delay=No delay2026.0379.6———————
CQLCategory=Non-diffusion, Delay=No delay2026.0379.2———————
HILPSetting=low-coverage2026.0356.34———————
PSMSetting=low-coverage2026.0355.7———————
FBSetting=low-coverage2026.0343.72———————
BCCategory=Non-diffusion, Delay=No delay2026.036.6———————
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—95.168.337.262.135.959.7—
EDAC2022.06—95.152.918.745.718.846.2—
LRTMode=lrt2025.10——————56810.79
LRT+QMode=lrt+q2025.10——————2,4484.94
QMode=q2025.10——————2,2825.28
RORL2022.06—94.19156.97143.371.2—
RORLEnsemble size K=102022.06—94.189.139.161.826.762.2—
SAC-10Ensemble size=102022.06—48.2372329.218.531.2—
SAC-10Ensemble size K=102022.06—47.730.113.821.310.724.7—