List your company
ResearchFormerly WizWand

Off-dynamics Reinforcement Learning on Ant MuJoCo

5,357Average RewardDARAIL
1,307.242,358.623,4104,461.38Nov 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DARAILDynamics Condition=Broken Source2024.115,357
GARATDynamics Condition=Broken Source2024.113,380
DAILDynamics Condition=Broken Source2024.113,239
IS-ACLDynamics Condition=Broken Source2024.112,753
MBPODynamics Condition=Broken Source2024.112,445
MATLDynamics Condition=Broken Source2024.112,006
IS-RDynamics Condition=Broken Source2024.111,463