Handbook of Learning and Approximate Dynamic Programming

Front Cover
Jennie Si
John Wiley & Sons, 2004 - Computers - 644 pages
2 Reviews
  • Presents fundamentals first: Java For Everyone takes a traditional path through the material, stressing control structures, methods, procedural decomposition, and arrays. Objects are used when appropriate in the early chapters. Students start designing and implementing their own classes in Chapter 7.
  • Practice makes perfect: Practice It pointers suggest exercises to try after each section, simple programming assignments, and a variety of online practice opportunities, including guided lab exercises, code completion questions, and skill-oriented multiple-choice questions provide ample opportunity for student programmers to practice what they are learning.
  • A visual approach motivates the reader and eases navigation: Step-by-step figures illustrate complex programming operations. Syntax boxes and example tables clearly present a variety of typical and special cases in a compact format. Visuals can be browsed by students prior to focusing on the textual material.
  • Guidance and worked examples help students succeed: While an activity as complex as programming cannot be reduced to cookbook-style instructions, step-by-step guidance is immensely helpful for building confidence and providing an outline for tasks at hand.

WileyPLUS is a research-based online environment for effective teaching and learning. WileyPLUS is packed with interactive study tools and resources-including the complete online textbook-to give your students more value for their money.

  

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

Foreword
1
Reinforcement Learning and Its Relationship to Supervised Learning
47
ModelBased Adaptive Critic Designs
65
Guidance in the Use of Adaptive Critics for Control
97
Direct Neural Dynamic Programming
125
The Linear Programming Approach to Approximate Dynamic
153
g Discussion
173
Reinforcement Learning in Large HighDimensional State Spaces
179
g Conclusion
279
Hierarchical Approaches to Concurrency Multiagency
285
Learning and Optimization From a System Theoretic Perspective
311
Robust Reinforcement Learning Using IntegralQuadratic
337
Supervised ActorCritic Reinforcement Learning
359
NearOptimal Control Via Reinforcement Learning
407
Multiobjective Control Problems by Reinforcement Learning
433
Adaptive Critic Based Neural Network for ControlConstrained
463

g Hierarchical Decision Making
203
Hierarchical Remforcement Learning in Theory
209
Hierarchical Remforcement Learning in Practice
217
IntraBehavior Learmng
223
Improved Temporal Difference Methods with Linear Function
235
Approximate Dynamic Programming for HighDimensional
261
Applications of Approximate Dynamic Programming in Power Systems
479
Robust Reinforcement Learning for floating Ventilation
517
Helicopter Flight Control Using Direct Neural Dynamic Programming
535
Toward Dynamic Stochastic Optimal Power Flow
561
Control Optimization Security and Selfhealing of Benchmark
599
Copyright

Common terms and phrases

References to this book

All Book Search results »

About the author (2004)

JENNIE SI is Professor of Electrical Engineering, Arizona State University, Tempe, AZ. She is director of Intelligent Systems Laboratory, which focuses on analysis and design of learning and adaptive systems. In addition to her own publications, she is the Associate Editor for IEEE Transactions on Neural Networks, and past Associate Editor for IEEE Transactions on Automatic Control and IEEE Transactions on Semiconductor Manufacturing. She was the co-chair for the 2002 NSF Workshop on Learning and Approximate Dynamic Programming.

ANDREW G. BARTO is Professor of Computer Science, University of Massachusetts, Amherst. He is co-director of the Autonomous Learning Laboratory, which carries out interdisciplinary research on machine learning and modeling of biological learning. He is a core faculty member of the Neuroscience and Behavior Program of the University of Massachusetts and was the co-chair for the 2002 NSF Workshop on Learning and Approximate Dynamic Programming. He currently serves as an associate editor of Neural Computation.

WARREN B. POWELL is Professor of Operations Research and Financial Engineering at Princeton University. He is director of CASTLE Laboratory, which focuses on real-time optimization of complex dynamic systems arising in transportation and logistics.

DONALD C. WUNSCH is the Mary K. Finley Missouri Distinguished Professor in the Electrical and Computer Engineering Department at the University of Missouri, Rolla. He heads the Applied Computational Intelligence Laboratory and also has a joint appointment in Computer Science, and is President-Elect of the International Neural Networks Society.

Bibliographic information