A Proposal for an Abstract Model Building Using Inductive Logic Programming

摘要：

Various ways of abstraction in reinforcement learning methods have been proposed. The central idea is to make use of the inherent structure in the MDP itself. Most traditional techniques do not scale up to even larger domains consisting of objects and relations. We present a proposal for abstract model building to construct relational Markov decision process. This approach separates the structural induction of the representation from the actual value function estimation. First a set of first-order features is induced utilizing inductive logic programming. These are then used as input for a regression algorithm that estimates Q-value functions per action in the induced states and determine a policy. In this way we hope to improve performance of standard Q-learaing.

关键词： Inductive logic programming Preimage Q-Iearning Reinforcement learning

作者: Zhi Li Xueli Yu Zengrong Liu Kun Hu

作者单位: College of Computer and Software in Taiyuan University of Technology 79 Yingze West Street, Taiyuan City, Shanxi Province, PRC Zip Code: 030024

会议类型: 国际会议

会议名称: International Conference on Computational Aspects of Social Networks(国际社会网络计算会议 CASoN 2010)

会议地点: 太原

会议语种:英文

页码: 348-350

在线出版日期: 2010-09-26（万方平台首次上网日期，不代表论文的发表时间）