List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo Hopper v2

4,408Average ReturnRESeL
1,164.242,006.372,848.53,690.63May 24, 2024
Updated 8mo ago

Evaluation results

MethodLinks
RESeLTime step=5M, Trials=62024.054,408
TD7Time step=5M, Trials=62024.054,075
TD3Time step=5M, Trials=62024.053,682
TQCTime step=1M, Trials=62024.053,526
TD7Time step=1M, Trials=62024.053,512
RESeLTime step=1M, Trials=62024.053,508
RESeLTime step=300k, Trials=62024.053,480
TQCTime step=5M, Trials=62024.053,462
TD3+OFETime step=5M, Trials=62024.053,423
TQCTime step=300k, Trials=62024.053,251
TD3Time step=1M, Trials=62024.053,226
SACTime step=5M, Trials=62024.053,167
TD3+OFETime step=1M, Trials=62024.053,121
TD7Time step=300k, Trials=62024.052,948
SACTime step=1M, Trials=62024.052,785
SACTime step=300k, Trials=62024.052,370
TD3+OFETime step=300k, Trials=62024.051,581
TD3Time step=300k, Trials=62024.051,289