List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo Humanoid v2

10,490Average ReturnRESeL
978.163,447.585,9178,386.42May 24, 2024
Updated 8mo ago

Evaluation results

MethodLinks
RESeLTime step=5M, Trials=62024.0510,490
TD7Time step=5M, Trials=62024.0510,281
TD3+OFETime step=5M, Trials=62024.058,951
TQCTime step=5M, Trials=62024.058,361
TD7Time step=1M, Trials=62024.057,429
RESeLTime step=1M, Trials=62024.057,280
SACTime step=5M, Trials=62024.056,555
TD3+OFETime step=1M, Trials=62024.056,032
TQCTime step=1M, Trials=62024.056,029
TD3Time step=5M, Trials=62024.055,433
TD7Time step=300k, Trials=62024.055,332
TD3Time step=1M, Trials=62024.055,165
SACTime step=1M, Trials=62024.054,909
RESeLTime step=300k, Trials=62024.054,578
TD3+OFETime step=300k, Trials=62024.053,181
TQCTime step=300k, Trials=62024.053,117
SACTime step=300k, Trials=62024.051,997
TD3Time step=300k, Trials=62024.051,344