Description |
1 online resource (643 pages) |
Series |
IEEE Press Series on Computational Intelligence |
|
IEEE series on computational intelligence.
|
Contents |
Reinforcement Learning And Approximate Dynamic Programming For Feedback Control; Contents; Preface; Contributors; Part I: Feedback Control Using RL and ADP; 1. Reinforcement Learning and Approximate Dynamic Programming (RLADP)-Foundations, Common Misconceptions, and the Challenges Ahead; 1.1 Introduction; 1.2 What is RLADP?; 1.2.1 Definition of RLADP and the Task it Addresses; 1.2.2 Basic Tools-Bellman Equation, and Value and Policy Functions; 1.2.3 Optimization Over Time Without Value Functions; 1.3 Some Basic Challenges in Implementing ADP; 1.3.1 Accounting for Unseen Variables |
|
1.3.2 Offline Controller Design Versus Real-Time Learning1.3.3 "Model-Based" Versus "Model Free" Designs; 1.3.4 How to Approximate the Value Function Better; 1.3.5 How to Choose u(t) Based on a Value Function; 1.3.6 How to Build Cooperative Multiagent Systems with RLADP; References; 2. Stable Adaptive Neural Control of Partially Observable Dynamic Systems; 2.1 Introduction; 2.2 Background; 2.3 Stability Bias; 2.4 Example Application; 2.4.1 The Simulated System; 2.4.2 An Uncertain Linear Plant Model; 2.4.3 The Closed Loop Control System |
|
2.4.4 Determining RNN Weight Updates by Reinforcement Learning2.4.5 Results; 2.4.6 Conclusions; References; 3. Optimal Control of Unknown Nonlinear Discrete-Time Systems Using the Iterative Globalized Dual Heuristic Programming Algorithm; 3.1 Background Material; 3.2 Neuro-Optimal Control Scheme Based on the Iterative ADP Algorithm; 3.2.1 Identification of the Unknown Nonlinear System; 3.2.2 Derivation of the Iterative ADP Algorithm; 3.2.3 Convergence Analysis of the Iterative ADP Algorithm; 3.2.4 Design Procedure of the Iterative ADP Algorithm |
|
3.2.5 NN Implementation of the Iterative ADP Algorithm Using GDHP Technique3.3 Generalization; 3.4 Simulation Studies; 3.5 Summary; References; 4. Learning and Optimization in Hierarchical Adaptive Critic Design; 4.1 Introduction; 4.2 Hierarchical ADP Architecture with Multiple-Goal Representation; 4.2.1 System Level Structure; 4.2.2 Architecture Design and Implementation; 4.2.3 Learning and Adaptation in Hierarchical ADP; 4.3 Case Study: The Ball-and-Beam System; 4.3.1 Problem Formulation; 4.3.2 Experiment Configuration and Parameters Setup; 4.3.3 Simulation Results and Analysis |
|
4.4 Conclusions and Future WorkReferences; 5. Single Network Adaptive Critics Networks-Development, Analysis, and Applications; 5.1 Introduction; 5.2 Approximate Dynamic Programing; 5.3 SNAC; 5.3.1 State Generation for Neural Network Training; 5.3.2 Neural Network Training; 5.3.3 Convergence Condition; 5.4 J-SNAC; 5.4.1 Neural Network Training; 5.4.2 Numerical Analysis; 5.5 Finite-SNAC; 5.5.1 Neural Network Training; 5.5.2 Convergence Theorems; 5.5.3 Numerical Analysis; 5.6 Conclusions; References; 6. Linearly Solvable Optimal Control; 6.1 Introduction; 6.1.1 Notation |
Summary |
Reinforcement learning (RL) and adaptive dynamic programming (ADP) has been one of the most critical research fields in science and engineering for modern complex systems. This book describes the latest RL and ADP techniques for decision and control in human engineered systems, covering both single player decision and control and multi-player games. Edited by the pioneers of RL and ADP research, the book brings together ideas and methods from many fields and provides an important and timely guidance on controlling a wide variety of systems, such as robots, industrial processes, and economic de |
Notes |
6.1.2 Markov Decision Processes |
Bibliography |
Includes bibliographical references and index |
Notes |
English |
|
Print version record |
Subject |
Reinforcement learning.
|
|
Feedback control systems.
|
|
TECHNOLOGY & ENGINEERING -- Electronics -- General.
|
|
COMPUTERS -- Cybernetics.
|
|
Feedback control systems
|
|
Reinforcement learning
|
Form |
Electronic book
|
Author |
Liu, Derong
|
LC no. |
2012027755 |
ISBN |
1118453980 |
|
9781118453988 |
|
9781118453971 |
|
1118453972 |
|
111810420X |
|
9781118104200 |
|
1299189857 |
|
9781299189850 |
|