List your company
ResearchFormerly WizWand

Reinforcement Learning on MuJoCo Walker2d v2

8,004Average ReturnRESeL
824.882,688.694,552.56,416.31May 24, 2024
Updated 8mo ago

Evaluation results

MethodLinks
RESeLTime step=5M, Trials=62024.058,004
TD7Time step=5M, Trials=62024.057,397
TD3+OFETime step=5M, Trials=62024.056,379
TQCTime step=5M, Trials=62024.056,137
TD7Time step=1M, Trials=62024.056,097
SACTime step=5M, Trials=62024.055,681
RESeLTime step=1M, Trials=62024.055,410
TD7Time step=300k, Trials=62024.055,379
TQCTime step=1M, Trials=62024.055,321
TD3+OFETime step=1M, Trials=62024.055,195
TD3Time step=5M, Trials=62024.055,078
RESeLTime step=300k, Trials=62024.054,373
SACTime step=1M, Trials=62024.054,314
TD3+OFETime step=300k, Trials=62024.054,018
TD3Time step=1M, Trials=62024.053,946
TQCTime step=300k, Trials=62024.052,812
SACTime step=300k, Trials=62024.051,989
TD3Time step=300k, Trials=62024.051,101