1-105 強化学習エージェントの確率的知識を用いた方策改善法に関する研究

概要

論文の詳細を見る
Reinforcement learning (RL) is a kind of machine learning, and aims to optimize policies of agents by adapting the agents to a given environment according to rewards. In this paper, we propose a method for improving policies by using stochastic knowledge, in which reinforcement learning agents obtain. We use a Bayesian Network (BN) as the knowledge of an agent. Its structure is decided by a model selection method based on information theory using series of an agent's input-output and rewards as sample data. The BN constructed in our study represents stochastic dependences between input-output and rewards. In our proposed method, agents' policies are improved by supervised learning using the structure of BN (i.e. stochastic knowledge). Introducing the mechanism of improving policies makes reinforcement learning agents acquire more effective policies. We carry out simulations in the pursuit problem in order to show the effectiveness of our proposed method.
社団法人日本機械学会の論文
2002-11-14