List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Halfcheetah Simultaneous Random Corruption

33.04Average ScoreTRACER
0.44648.908217.3725.8318Nov 1, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TRACER2024.1133.04
RIQL2024.1129.94
IQL2024.1124.82
BC2024.1123.17
CQL2024.1114.25
MSG2024.119.97
UWMSG2024.118.31
EDAC2024.111.7