List your company
ResearchFormerly WizWand

Off-dynamics Reinforcement Learning on MuJoCo Walker2d 0.5 density dynamics shift (test)

2,729RewardOptimal in Target
694.761,222.881,7512,279.12Nov 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Optimal in Target2024.112,729
DARCSetup=DARC Training2024.112,449
DARAIL2024.111,595
DARCSetup=DARC Evaluation2024.11773