List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo HalfCheetah v2

18,165Average ReturnTD7
6,559.649,572.5712,585.515,598.43May 24, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TD7Time step=5M, Trials=62024.0518,165
TQCTime step=5M, Trials=62024.0517,459
TD7Time step=1M, Trials=62024.0517,434
RESeLTime step=5M, Trials=62024.0516,750
TD3+OFETime step=5M, Trials=62024.0516,596
SACTime step=5M, Trials=62024.0515,526
TD7Time step=300k, Trials=62024.0515,031
TD3Time step=5M, Trials=62024.0514,337
TD3+OFETime step=1M, Trials=62024.0513,758
TQCTime step=1M, Trials=62024.0512,349
RESeLTime step=1M, Trials=62024.0512,327
TD3+OFETime step=300k, Trials=62024.0511,294
TD3Time step=1M, Trials=62024.0510,574
SACTime step=1M, Trials=62024.0510,484
RESeLTime step=300k, Trials=62024.059,456
SACTime step=300k, Trials=62024.058,052
TD3Time step=300k, Trials=62024.057,715
TQCTime step=300k, Trials=62024.057,006