List your company
ResearchFormerly WizWand

Reinforcement Learning on AntMaze Large Play

46.7OSRRankQ
-1.86810.74123.3535.959May 11, 2026
Updated 5mo ago

Evaluation results

MethodLinks
RankQvariant=+SAC2026.0546.70
CQLvariant=+SAC2026.0543.30
Cal-QL2026.0536.767.7
RankQ2026.0536.791.2
Cal-QLvariant=+SAC2026.05300
CQL2026.0528.382.8
Hybrid RL2026.0500
SAC2026.0500
SACvariant=+OFF2026.0500