List your company

Continuous Control on HumanoidBench (w/ Hand)

733Return (Slide)PO-MPC
-7.48184.76377569.24Oct 5, 2025Nov 10, 2025Dec 17, 2025Jan 22, 2026Feb 28, 2026Apr 5, 2026May 12, 2026

Evaluation results

MethodLinks
PO-MPClambda=12025.10733—326——933839—960984—90793093172.3——68363218347
PO-MPClambda=92025.10620—339——935914—908982—88493293474.4——69690203354
PO-MPClambda=0.12025.10451—108——919902—338978—89989383453.2——6269221234
BMPC2025.10314—81——932821—775966—82893293259——5887196350
DR.QEnvironment Steps=1M, Action Repeat=22026.05285320288709349942891754245264,95012949151245.252.953.4————
FoGEnvironment Steps=1M, Action Repeat=22026.052012441356105776311791822577942,87722797525.434.233.6————
TD-MPC22025.10174—58——912245—142946—14988663425.5——666697275
MR.QEnvironment Steps=1M, Action Repeat=22026.05146293127691332653487532378074,101353009528.638.838.5————
SimbaV2Environment Steps=1M, Action Repeat=22026.05136310120838496927724564936403,223301036429.84241.7————
TDMPC2Environment Steps=1M, Action Repeat=22026.057913443973460713947998973,610291932341529.828.2————
SimBaEnvironment Steps=1M, Action Repeat=22026.056720661487490643649542247793,185311279421.935.634.5————
DreamerV3Environment Steps=1M, Action Repeat=22026.05211016452748151348256864641191.92.12————