List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Hopper Simultaneous Adversarial Corruption

24.8Average ScoreTRACER
-0.8885.78112.4519.119Nov 1, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TRACER2024.1124.8
RIQL2024.1124.71
IQL2024.1119.56
BC2024.1117.34
MSG2024.1112.14
UWMSG2024.1110.43
EDAC2024.110.8
CQL2024.110.1