List your company

Offline Reinforcement Learning on halfcheetah medium v2

4,452Average ScoreLRT+Q
-176.7281,024.9612,226.653,428.339Jun 6, 2022Jan 21, 2023Sep 8, 2023Apr 25, 2024Dec 11, 2024Jul 29, 2025Mar 16, 2026

Evaluation results

MethodLinks
LRT+QMode=lrt+q2025.104,452—————5.02
QMode=q2025.104,404—————5.11
LRTMode=lrt2025.103,526—————3.61
ReBRACCategory=Non-diffusion, Delay=No delay2026.0366.4——————
SAIDCategory=Diffusion Planners, Delay=02026.0358.5——————
DQL*Category=Diffusion Policies, Delay=No delay2026.0352.6——————
DQLCategory=Diffusion Policies, Delay=No delay2026.0351.1——————
DVCategory=Diffusion Planners, Delay=No delay2026.0350.4——————
RLDPSetting=low-coverage2026.0349.08——————
SAIDCategory=Diffusion Planners, Delay=42026.0345.2——————
CQLCategory=Non-diffusion, Delay=No delay2026.0344.4——————
HILPSetting=low-coverage2026.0343.85——————
RORL2022.0643.658.649.53843.528.2—
DiffuserCategory=Diffusion Planners, Delay=No delay2026.0342.8——————
PSMSetting=low-coverage2026.0342.64——————
SAC-10Ensemble size=102022.0641.160.145.634.239.825.7—
EDAC2022.064059.244.53338.125—
FBSetting=low-coverage2026.0339.27——————
RORLEnsemble size K=102022.0637.257.444.529.73717.7—
BCCategory=Non-diffusion, Delay=No delay2026.0336.1——————
SAC-10Ensemble size K=102022.0633.457.938.325.130.814.9—
EDAC2022.0632.2573723.928.714.4—
SAIDCategory=Diffusion Planners, Delay=82026.035.8——————
DQL+SACategory=Baseline w/ delay, Delay=42026.032.4——————
DQL+SACategory=Baseline w/ delay, Delay=82026.032——————
SAIDCategory=Diffusion Planners, Delay=162026.031.5——————
DQL+SACategory=Baseline w/ delay, Delay=162026.031.3——————