List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on D4RL Walker2d Simultaneous Random Corruption

23.62Average ScoreTRACER
-1.10085.317111.73518.1529Nov 1, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TRACER2024.1123.62
RIQL2024.1117.42
BC2024.1113.77
IQL2024.1112.35
UWMSG2024.114.36
CQL2024.110.63
EDAC2024.11-0.13
MSG2024.11-0.15