深層強化学習のハイパーパラメータと報酬関数のベイズ最適化：移動ロボットの行動獲得への適用

カテゴリ: 部門大会

論文No: TC11-2-4

グループ名: 【C】2024年電気学会電子・情報・システム部門大会

発行日: 2024/08/28

タイトル(英語): Bayesian Optimization of Hyper-Parameters and Reward Function in Deep Reinforcement Learning: Application to Behavior Acquisition of Mobile Robot

著者名: 曽田 涼介（奈良先端科学技術大学院大学）,西村 拓人（松江工業高等専門学校）,堀内 匡（松江工業高等専門学校）

著者名(英語): Ryosuke Sota (Nara Institute of Science and Technology),Takuto Nishimura (National Institute of Technology, Matsue College),Tadashi Horiuchi (National Institute of Technology, Matsue College)

キーワード: 深層強化学習|ベイズ最適化|移動ロボット|行動獲得|Deep Reinforcement Learning|Bayesian Optimization|Mobile Robot|Behavior Acquisition

要約(日本語): Deep reinforcement learning is a machine learning method that combines deep learning and reinforcement learning. Deep Q-network (DQN) is one of the typical methods of deep reinforcement learning. We have applied DQN method to the mobile robot navigation problem. The values of hyper-parameters including the network structure of DQN, and the reward function have been determined empirically. In this study, we attempt to optimize the values of hyper-parameters and reward function of deep reinforcement learning by Optuna, a framework of Bayesian optimization. We confirmed that the values of hyper-parameters and reward function obtained by Optuna have higher learning performance than that by empirical method.