Adaptive Representations for Reinforcement Learning (Studies in Computational Intelligence) by Shimon Whiteson, PDF 3642422314

Adaptive Representations for Reinforcement Learning (Studies in Computational Intelligence)

  • Title: Adaptive Representations for Reinforcement Learning (Studies in Computational Intelligence)
  • Autor: Shimon Whiteson
  • Publisher (Publication Date): Springer; 2010 edition (November 14, 2014)
  • Language: English
  • ISBN-10: | 3642422314
  • ISBN-13: | 978-3642422317
  • File Format: EPUB, PDF

 
This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.

No reviews

Comments:


Related posts

Adobe Captivate 2017: The Essentials by Kevin Siegel, PDF 1944607102
Biometric Recognition: 12th Chinese Conference, CCBR 2017, Shenzhen, China, October 28-29, 2017, Proceedings (Lecture Notes in Computer Science) by , PDF 3319699229
Industry 4.0: Managing The Digital Transformation (Springer Series in Advanced Manufacturing) by Emre Cevikcan, PDF
Hacking for Beginners: Learn basics of computer hacking in no time! by Nicholas Brown, PDF 1542496195
Communications, Signal Processing, and Systems: Proceedings of the 2016 International Conference on Communications, Signal Processing, and Systems (Lecture Notes in Electrical Engineering) by Baoju Zhang, PDF
SEO Made Simple (6th Edition): Insider Secrets for Driving More Traffic to Your Website by Michael H. Fleischner, PDF 1546308520

Leave a Reply

Your email address will not be published. Required fields are marked *