List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo Ant v2

10,133Average ReturnTD7
1,131.83,468.655,805.58,142.35May 24, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TD7Time step=5M, Trials=62024.0510,133
TD3+OFETime step=5M, Trials=62024.058,547
TD7Time step=1M, Trials=62024.058,509
RESeLTime step=5M, Trials=62024.058,006
TD3+OFETime step=1M, Trials=62024.057,398
TD3+OFETime step=300k, Trials=62024.056,348
TQCTime step=5M, Trials=62024.056,329
RESeLTime step=1M, Trials=62024.056,295
TD7Time step=300k, Trials=62024.056,171
TD3Time step=5M, Trials=62024.055,589
SACTime step=5M, Trials=62024.054,615
RESeLTime step=300k, Trials=62024.054,181
TD3Time step=1M, Trials=62024.053,942
SACTime step=1M, Trials=62024.053,681
TQCTime step=1M, Trials=62024.053,582
TQCTime step=300k, Trials=62024.051,830
TD3Time step=300k, Trials=62024.051,704
SACTime step=300k, Trials=62024.051,478