List your company
ResearchFormerly WizWand

Off-dynamics Reinforcement Learning on Walker2d MuJoCo

4,366Average RewardDARAIL
85.361,196.682,3083,419.32Nov 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DARAILDynamics Condition=Broken Source2024.114,366
IS-ACLDynamics Condition=Broken Source2024.113,881
GARATDynamics Condition=Broken Source2024.113,296
IS-RDynamics Condition=Broken Source2024.113,092
DAILDynamics Condition=Broken Source2024.112,330
MBPODynamics Condition=Broken Source2024.111,012
MATLDynamics Condition=Broken Source2024.11250