Catalog
- Results include
-
Algorithms for reinforcement learning
Szepesvári, CsabaCham, Switzerland : Springer, ©2010.Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming. We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations.
Online SpringerLink
-
Algorithms for reinforcement learning [electronic resource]
Szepesvári, CsabaSan Rafael, Calif. (1537 Fourth Street, San Rafael, CA 94901 USA) : Morgan & Claypool, c2010.Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations. Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research or control engineering. In this book, we focus on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming. We give a fairly comprehensive catalog of learning problems, describe the core ideas, note a large number of state of the art algorithms, followed by the discussion of their theoretical properties and limitations.
Online Synthesis Digital Library
-
Performance of nonlinear approximate adaptive controllers
French, MarkChichester ; Hoboken, NJ : Wiley, c2003.In recent years, there has been a wide interest in non-linear adaptive control using approximate models, either for tracking or regulation, and usually under the banner of neural network based control. The authors present a unique critical evaluation of the approximate model philosophy and its setting, rigorously comparing the performance of such controls against competing designs. Analysing a very topical aspect of contemporary research and control practice, this book highlights the situations in which approximate model based designs are most appropriate and indicates scenarios in which other designs could be used more productively. Throughout the text concepts are illustrated using a variety of examples, both academic problems and those based on physical examples. The work is designed to open the door to realistic applications. It provides a unified coverage of the theory and application of a wide range of control systems areas including neural network based control and control using the approximate model. It presents a mathematically well founded introduction to the area of intelligent control. It provides a varied selection of practical examples drawn from a variety of fields, including robotics and aerospace, illustrate theoretical principles. It gives clear comparisons of a variety of control designs and offers cross disciplinary approach to this leading edge topic. It is a valuable reference for control practitioners and theorists, artificial intelligence researchers and applied mathematicians, as well as graduate students and researchers with an interest in adaptive control and stability.
Online Wiley Online Library
Guides
Library website
Exhibits
EarthWorks
More search tools
Tools to help you discover resources at Stanford and beyond.
