List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on 1T10S Walker2D (Medium)

80.693ScoreDFDT
1.8953222.3524142.809563.26659Oct 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DFDTDistribution Shift=BodyMass2024.1080.693
IGDFDistribution Shift=JointNoise2024.1080.549
IGDFDistribution Shift=BodyMass2024.1078.271
D-AWRDistribution Shift=BodyMass2024.1078.004
AWRDistribution Shift=BodyMass2024.1077.442
DFDTDistribution Shift=JointNoise2024.1076.373
D-CQLDistribution Shift=BodyMass2024.1074.276
CQLDistribution Shift=BodyMass2024.1073.317
H2ODistribution Shift=JointNoise2024.1072.849
D-BCQDistribution Shift=BodyMass2024.1072.023
BCQDistribution Shift=BodyMass2024.1070.681
D-CQLDistribution Shift=JointNoise2024.1069.141
CQLDistribution Shift=JointNoise2024.1068.962
AWRDistribution Shift=JointNoise2024.1067.636
D-AWRDistribution Shift=JointNoise2024.1064.303
H2ODistribution Shift=BodyMass2024.1063.031
BCQDistribution Shift=JointNoise2024.1062.696
D-BCQDistribution Shift=JointNoise2024.1060.681
D-MOPODistribution Shift=JointNoise2024.1023.57
MOPODistribution Shift=JointNoise2024.1023.552
D-MOPODistribution Shift=BodyMass2024.1021.621
MOPODistribution Shift=BodyMass2024.1021.617
D-BEARDistribution Shift=JointNoise2024.106.933
D-BEARDistribution Shift=BodyMass2024.106.516
BEARDistribution Shift=BodyMass2024.105.776
BEARDistribution Shift=JointNoise2024.104.926