List your company

Offline Reinforcement Learning on halfcheetah medium-replay v2

51.2Normalized ScoreReBRAC
-1.8411.9325.739.47Mar 2, 2026

Evaluation results

MethodLinks
ReBRACCategory=Non-diffusion, Delay=No delay2026.0351.2——
SAIDCategory=Diffusion Planners, Delay=02026.0350.2——
DQL*Category=Diffusion Policies, Delay=No delay2026.0348.9——
DQLCategory=Diffusion Policies, Delay=No delay2026.0347.8——
CQLCategory=Non-diffusion, Delay=No delay2026.0346.2——
DVCategory=Diffusion Planners, Delay=No delay2026.0345.8——
BCCategory=Non-diffusion, Delay=No delay2026.0338.4——
DiffuserCategory=Diffusion Planners, Delay=No delay2026.0337.7——
SAIDCategory=Diffusion Planners, Delay=42026.0334.3——
SAIDCategory=Diffusion Planners, Delay=82026.038.3——
SAIDCategory=Diffusion Planners, Delay=162026.032.1——
DQL+SACategory=Baseline w/ delay, Delay=82026.031.4——
DQL+SACategory=Baseline w/ delay, Delay=162026.031.3——
DQL+SACategory=Baseline w/ delay, Delay=42026.030.2——
LRTMode=lrt2025.10—5581.14
LRT+QMode=lrt+q2025.10—61513.93
QMode=q2025.10—59813.13