List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on antmaze large-play

78.2ScoreGCPC
-3.12817.98639.160.214Jun 6, 2022Aug 11, 2022Oct 16, 2022Dec 21, 2022Feb 25, 2023May 2, 2023Jul 7, 2023
Updated 8mo ago

Evaluation results

MethodLinks
GCPC2023.0778.2
TAP2023.0774
IQL2023.0750
GCIQL2023.0740
IQL2022.0639.6
IQL+smoothing2022.0638.3
CQL2023.0736.4
RvS-G2023.0735.6
ROMI+BCQ2022.0620.2
RORL2022.0616.3
CQL2022.0615.8
DWSL2023.0715.2
WGCSL2023.070.6
TD3+BC2022.060.2
BC2022.060
AWAC2022.060
BC2023.070
DT2023.070