スケジュール 0 15:40 〜 15:50 [E-O2-04] Navigate towards humans through deep reinforcement learning (C000110) *alireza ahmadi1, Wan Zuha Wan Hasan1, Nasri Sulaiman1, Hakaru Tamukoh2 (1. universiti putra malaysia, 2. Kyushu Institute of Technology) キーワード:Human Support Robot (HSR), reinforcement learning(RL), navigation, robot