List your company

Offline Reinforcement Learning on hopper medium v2

102Normalized ScoreDQL*
-2255279Mar 2, 2026

Evaluation results

MethodLinks
DQL*Category=Diffusion Policies, Delay=No delay2026.03102——————
ReBRACCategory=Non-diffusion, Delay=No delay2026.0391.1——————
DQLCategory=Diffusion Policies, Delay=No delay2026.0390.5——————
SAIDCategory=Diffusion Planners, Delay=162026.0386.6——————
SAIDCategory=Diffusion Planners, Delay=02026.0384.6——————
DVCategory=Diffusion Planners, Delay=No delay2026.0383.6——————
SAIDCategory=Diffusion Planners, Delay=82026.0383.5——————
SAIDCategory=Diffusion Planners, Delay=42026.0382——————
DiffuserCategory=Diffusion Planners, Delay=No delay2026.0374.3——————
CQLCategory=Non-diffusion, Delay=No delay2026.0358——————
BCCategory=Non-diffusion, Delay=No delay2026.0329——————
DQL+SACategory=Baseline w/ delay, Delay=42026.033.1——————
DQL+SACategory=Baseline w/ delay, Delay=82026.032——————
DQL+SACategory=Baseline w/ delay, Delay=162026.032——————
EDAC2022.06—7,2206,9704,55038.323.74,990
EDAC2022.06—61.761.430.821.79.637
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—8,4807,8405,39051.534.76,070
RORLEnsemble size K=102022.06—766836.137.421.147.7
SAC-10Ensemble size=102022.06—7982890.881.3695
SAC-10Ensemble size K=102022.06—0.80.840.930.911.671.03