[10a-W321-1~10] 23.1 Joint Session N "Informatics"

△ [10a-W321-10] Reinforcement learning and decision making using laser chaos for multi-arm bandit problem with variable hit probabilities

〇Akihiro Oda¹, Takatomo Mihana¹, Kazutaka Kanno¹, Makoto Naruse², Atsushi Uchida¹ (1.Saitama Univ., 2.NICT)

Keywords:reinforcement learning, laser chaos, decision making