List your company
ResearchFormerly WizWand

Locomotion on Hopper IID (test)

1,859Mean Episode RewardRMA
426.92798.711,170.51,542.29Sep 28, 2022
Updated 8mo ago

Evaluation results

MethodLinks
RMAsigma=0.1, protocol=train sigma = test sigma2022.091,859
Oraclesigma=0.1, protocol=train sigma = test sigma2022.091,859
DMAPsigma=0.12022.091,842
DMAPsigma=0.1, protocol=train sigma = test sigma2022.091,842
Simplesigma=0.1, protocol=train sigma = test sigma2022.091,807
TCNsigma=0.12022.091,762
TCNsigma=0.1, protocol=train sigma = test sigma2022.091,762
TCNsigma=0.32022.091,368
TCNsigma=0.3, protocol=train sigma = test sigma2022.091,368
DMAPsigma=0.32022.091,316
DMAPsigma=0.3, protocol=train sigma = test sigma2022.091,316
Oraclesigma=0.3, protocol=train sigma = test sigma2022.091,296
RMAsigma=0.3, protocol=train sigma = test sigma2022.091,267
Simplesigma=0.3, protocol=train sigma = test sigma2022.091,121
TCNsigma=0.52022.091,017
TCNsigma=0.5, protocol=train sigma = test sigma2022.091,017
DMAP-nesigma=0.1, protocol=train sigma = test sigma2022.09984
DMAPsigma=0.52022.09953
DMAPsigma=0.5, protocol=train sigma = test sigma2022.09953
Oraclesigma=0.5, protocol=train sigma = test sigma2022.09919
Simplesigma=0.5, protocol=train sigma = test sigma2022.09863
DMAP-nesigma=0.3, protocol=train sigma = test sigma2022.09748
RMAsigma=0.5, protocol=train sigma = test sigma2022.09730
DMAP-nesigma=0.5, protocol=train sigma = test sigma2022.09482