[D-8] 人工知能と知識処理

9:15 AM - 9:30 AM JST(12:15 AM - 12:30 AM UTC)

[D-8-10] Automatic Acquisition of Reward Function through Inverse Reinforcement Learning in a Control System Integrating Fuzzy Reasoning and Policy Gradient Reinforcement Learning

○Reo Kojima¹, Seiji Ishihara² (1. Graduate School of Tokyo Denki Univ., 2. Tokyo Denki Univ.)

Keywords:

inverse reinforcement learning,fuzzy reasoning,policy gradient reinforcement learning