List your company

Offline Reinforcement Learning on HalfCheetah vel

-1,026Maximum episode returnRADT
-4,931.7616-3,917.7658-2,903.77-1,889.7742May 27, 2026

Evaluation results

MethodLinks
RADTTarget Velocity=7.0, Horizon=10002026.05-1,026
DCTarget Velocity=6.0, Horizon=10002026.05-1,061.06
RADTTarget Velocity=6.0, Horizon=10002026.05-1,085.82
DTTarget Velocity=6.0, Horizon=10002026.05-1,094.22
Q-ALIGN DTTarget Velocity=6.0, Horizon=10002026.05-1,203.69
Q-ALIGN DTTarget Velocity=5.0, Horizon=10002026.05-1,246.46
Q-ALIGN DTTarget Velocity=4.0, Horizon=10002026.05-1,289.17
DCTarget Velocity=5.0, Horizon=10002026.05-1,332.75
Q-ALIGN DTTarget Velocity=7.0, Horizon=10002026.05-1,441.51
Q-ALIGN DTTarget Velocity=10.0, Horizon=10002026.05-1,493.27
DTTarget Velocity=5.0, Horizon=10002026.05-1,573.92
Q-ALIGN DTTarget Velocity=Mean, Horizon=10002026.05-1,637.54
RADTTarget Velocity=4.0, Horizon=10002026.05-1,709.06
DTTarget Velocity=4.0, Horizon=10002026.05-1,744.94
DCTarget Velocity=4.0, Horizon=10002026.05-1,749.01
QTTarget Velocity=4.0, Horizon=10002026.05-1,899.36
RADTTarget Velocity=8.0, Horizon=10002026.05-2,100.74
DCTarget Velocity=10.0, Horizon=10002026.05-2,162.07
RADTTarget Velocity=Mean, Horizon=10002026.05-2,217.85
QTTarget Velocity=6.0, Horizon=10002026.05-2,247.88
DCTarget Velocity=Mean, Horizon=10002026.05-2,334.44
Q-ALIGN DTTarget Velocity=8.0, Horizon=10002026.05-2,366.28
DTTarget Velocity=10.0, Horizon=10002026.05-2,412.16
Q-ALIGN DTTarget Velocity=9.0, Horizon=10002026.05-2,422.39
RADTTarget Velocity=5.0, Horizon=10002026.05-2,452.64
DTTarget Velocity=Mean, Horizon=10002026.05-2,543.41
QTTarget Velocity=5.0, Horizon=10002026.05-2,716.32
DCTarget Velocity=9.0, Horizon=10002026.05-2,850.36
DTTarget Velocity=9.0, Horizon=10002026.05-3,249.43
RADTTarget Velocity=10.0, Horizon=10002026.05-3,261.8
QTTarget Velocity=Mean, Horizon=10002026.05-3,332.88
DCTarget Velocity=8.0, Horizon=10002026.05-3,519.51
QTTarget Velocity=10.0, Horizon=10002026.05-3,528.83
DTTarget Velocity=7.0, Horizon=10002026.05-3,627.29
DCTarget Velocity=7.0, Horizon=10002026.05-3,666.29
RADTTarget Velocity=9.0, Horizon=10002026.05-3,888.88
QTTarget Velocity=7.0, Horizon=10002026.05-3,967.86
DTTarget Velocity=8.0, Horizon=10002026.05-4,101.9
QTTarget Velocity=9.0, Horizon=10002026.05-4,188.4
QTTarget Velocity=8.0, Horizon=10002026.05-4,781.54