List your company
ResearchFormerly WizWand

Off-dynamics Reinforcement Learning on HalfCheetah broken source environment MuJoCo

7,067Average RewardDARAIL
1,316.842,809.674,302.55,795.33Nov 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DARAILDynamics Condition=Broken Source2024.117,067
IS-ACLDynamics Condition=Broken Source2024.116,934
DAILDynamics Condition=Broken Source2024.116,402
IS-RDynamics Condition=Broken Source2024.116,007
GARATDynamics Condition=Broken Source2024.115,877
MBPODynamics Condition=Broken Source2024.114,323
MATLDynamics Condition=Broken Source2024.111,538