[2J6-GS-2] Machine learning: Advancement reinforcement learning (2)

[2J6-GS-2-04] Visual explanation using Attention mechanism in A3C

〇Hidenori Itaya¹, Tsubasa Hirakawa¹, Takayoshi Yamashita¹, Hironobu Fujiyoshi¹, Komei Sugiura² (1. Chubu University, 2. National Institute of Information and Communications Technology (NICT))

Keywords:Reinforcement learning, Visual explanation

Asynchronous Advantage Actor-Critic (A3C) is a representative method of deep reinforcement learning and is possible to solve difficult tasks such as games and robot control. However, it is difficult for deep reinforcement learning including A3C to understand and to explain the reason of action selection. To address this problem, we propose a method called a Mask-Attention A3C, which performs mask processing on feature map of Policy branch using attention map. The propose method can obtain an attention map that is useful for a visual explanation of agent behavior. In the experiment with Atari2600, we compare the scores in each game and demonstrate that the attention map obtained from our method is useful for visual explanation. In addition, we evaluate the explainability of obtained attention map using the scores of each game by changing the attention region.