Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Visual Reinforcement Learning on DMControl VDCS Markov-temporal perturbations (test)

864Cartpole Swingup Score

ACO-MoE

16.4236.45456.5676.55Apr 27, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
864492882910339700963738736
2026.04
6833792331016530944357296.1
2026.04
649961606941221837279389.6
2026.04
6153075947544158171128244.6
2026.04
613778316033237845188412.3
2026.04
35494828756166792229348.4
2026.04
3425451056591094532232316.1
2026.04
49268436452525.3