[3S08m] 大会企画シンポジウム
意思決定研究における理論と実験の融合

[3S08m-02] A distributional code for value in dopamine-based reinforcement learning

*Will Dabney¹、Zebulun Lloyd Kurth-Nelson¹、Naoshige Uchida²、Clara K Starkweather²、Demis Hassabis¹、Rémi Munos¹、Matthew Botvinick¹ (1. DeepMind、2. Center for Brain Science, Department of Molecular and Cellular Biology, Harvard University)