首页 | 本学科首页   官方微博 | 高级检索  
     


Basis Function Adaptation in Temporal Difference Reinforcement Learning
Authors:Ishai?Menache,Shie?Mannor  author-information"  >  author-information__contact u-icon-before"  >  mailto:shie@ece.mcgill.ca"   title="  shie@ece.mcgill.ca"   itemprop="  email"   data-track="  click"   data-track-action="  Email author"   data-track-label="  "  >Email author,Nahum?Shimkin
Affiliation:(1) Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel;(2) Department of Electrical and Computer Engineering, McGill University, 3480 University Street, Montreal, Quebec, Canada;(3) Department of Electrical Engineering, Technion, Israel Institute of Technology, Haifa, 32000, Israel
Abstract:Reinforcement Learning (RL) is an approach for solving complex multi-stage decision problems that fall under the general framework of Markov Decision Problems (MDPs), with possibly unknown parameters. Function approximation is essential for problems with a large state space, as it facilitates compact representation and enables generalization. Linear approximation architectures (where the adjustable parameters are the weights of pre-fixed basis functions) have recently gained prominence due to efficient algorithms and convergence guarantees. Nonetheless, an appropriate choice of basis function is important for the success of the algorithm. In the present paper we examine methods for adapting the basis function during the learning process in the context of evaluating the value function under a fixed control policy. Using the Bellman approximation error as an optimization criterion, we optimize the weights of the basis function while simultaneously adapting the (non-linear) basis function parameters. We present two algorithms for this problem. The first uses a gradient-based approach and the second applies the Cross Entropy method. The performance of the proposed algorithms is evaluated and compared in simulations. This research was partially supported by the Fund for Promotion of Research at the Technion. The work of S.M. was partially supported by the National Science Foundation under grant ECS-0312921.
Keywords:reinforcement learning  temporal difference algorithms  cross entropy method  radial basis functions
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号