Handbook of Learning and Approximate Dynamic Programming

Description

A complete resource to Approximate Dynamic Programming (ADP), including on-line simulation code Provides a tutorial that readers can use to start implementing the learning algorithms provided in the book Includes ideas, directions, and recent results on current research issues and addresses applications where ADP has been successfully implemented The contributors are leading researchers in the field Content: Chapter 1 ADP: Goals, Opportunities and Principles (pages 3–44): Paul WerbosChapter 2 Reinforcement Learning and Its Relationship to Supervised Learning (pages 45–63): Andrew G. Barto and Thomas G. DietterichChapter 3 Model?Based Adaptive Critic Designs (pages 65–95): Silvia Ferrari and Robert F. StengelChapter 4 Guidance in the Use of Adaptive Critics for Control (pages 97–124): George G. Lendaris and James C. NeidhoeferChapter 5 Direct Neural Dynamic Programming (pages 125–151): Jennie Si, Lei Yang and Derong LiuChapter 6 The Linear Programming Approach to Approximate Dynamic Programming (pages 153–178): Daniela Pucci de FariasChapter 7 Reinforcement Learning in Large, High?Dimensional State Spaces (pages 179–202): Greg Grudic and Lyle UngarChapter 8 Hierarchical Decision Making (pages 203–232): Malcolm RyanChapter 9 Improved Temporal Difference Methods with Linear Function Approximation (pages 233–259): Dimitri P. Bertsekas, Vivek S. Borkar and Angelia NedichChapter 10 Approximate Dynamic Programming for High?Dimensional Resource Allocation Problems (pages 261–283): Warren B. Powell and Benjamin Van RoyChapter 11 Hierarchical Approaches to Concurrency, Multiagency, and Partial Observability (pages 285–310): Sridhar Mahadevan, Mohammad Ghavamzadeh, Khashayar Rohanimanesh and Georgias TheocharousChapter 12 Learning and Optimization — From a System Theoretic Perspective (pages 311–335): Xi?Ren CaoChapter 13 Robust Reinforcement Learning Using Integral?Quadratic Constraints (pages 337–358): Charles W. Anderson, Matt Kretchmar, Peter Young and Douglas HittleChapter 14 Supervised Actor?Critic Reinforcement Learning (pages 359–380): Michael T. Rosenstein and Andrew G. BartoChapter 15 BPTT and DAC — A Common Framework for Comparison (pages 381–404): Danil V. ProkhorovChapter 16 Near?Optimal Control Via Reinforcement Learning and Hybridization (pages 405–432): Augustine O. Esogbue and Warren E. HearnesChapter 17 Multiobjective Control Problems by Reinforcement Learning (pages 433–461): Dong?Oh Kang and Zeungnam BienChapter 18 Adaptive Critic Based Neural Network for Control?Constrained Agile Missile (pages 463–478): S. N. Balakrishnan and Dongchen HanChapter 19 Applications of Approximate Dynamic Programming in Power Systems Control (pages 479–515): Ganesh K Venayagamoorthy, Donald C Wunsch and Ronald G HarleyChapter 20 Robust Reinforcement Learning for Heating, Ventilation, and Air Conditioning Control of Buildings (pages 517–534): Charles W. Anderson, Douglas Hittle, Matt Kretchmar and Peter YoungChapter 21 Helicopter Flight Control Using Direct Neural Dynamic Programming (pages 535–559): Russell Enns and Jennie SiChapter 22 Toward Dynamic Stochastic Optimal Power Flow (pages 561–598): James A. MomohChapter 23 Control, Optimization, Security, and Self?healing of Benchmark Power Systems (pages 599–634): James A. Momoh and Edwin Zivi