Simulation-based Algorithms for Markov Decision Processes

Markov decision process (MDP) models are widely used for modeling sequential decision-making problems that arise in engineering, economics, computer science, and the social sciences. It is well-known that many real-world problems modeled by MDPs have huge

  • PDF / 2,219,252 Bytes
  • 202 Pages / 439.37 x 666.142 pts Page_size
  • 62 Downloads / 206 Views

DOWNLOAD

REPORT


Series Editors E.D. Sontag · M. Thoma · A. Isidori · J.H. van Schuppen

Published titles include: Stability and Stabilization of Infinite Dimensional Systems with Applications Zheng-Hua Luo, Bao-Zhu Guo and Omer Morgul Nonsmooth Mechanics (Second edition) Bernard Brogliato Nonlinear Control Systems II Alberto Isidori L2 -Gain and Passivity Techniques in Nonlinear Control Arjan van der Schaft Control of Linear Systems with Regulation and Input Constraints Ali Saberi, Anton A. Stoorvogel and Peddapullaiah Sannuti Robust and H∞ Control Ben M. Chen Computer Controlled Systems Efim N. Rosenwasser and Bernhard P. Lampe Control of Complex and Uncertain Systems Stanislav V. Emelyanov and Sergey K. Korovin Robust Control Design Using H∞ Methods Ian R. Petersen, Valery A. Ugrinovski and Andrey V. Savkin Model Reduction for Control System Design Goro Obinata and Brian D.O. Anderson Control Theory for Linear Systems Harry L. Trentelman, Anton Stoorvogel and Malo Hautus

Non-linear Control for Underactuated Mechanical Systems Isabelle Fantoni and Rogelio Lozano Robust Control (Second edition) Jürgen Ackermann Flow Control by Feedback Ole Morten Aamo and Miroslav Krsti´c Learning and Generalization (Second edition) Mathukumalli Vidyasagar Constrained Control and Estimation Graham C. Goodwin, María M. Seron and José A. De Doná Randomized Algorithms for Analysis and Control of Uncertain Systems Roberto Tempo, Giuseppe Calafiore and Fabrizio Dabbene Switched Linear Systems Zhendong Sun and Shuzhi S. Ge Subspace Methods for System Identification Tohru Katayama Digital Control Systems Ioan D. Landau and Gianluca Zito Multivariable Computer-controlled Systems Efim N. Rosenwasser and Bernhard P. Lampe Dissipative Systems Analysis and Control (Second edition) Bernard Brogliato, Rogelio Lozano, Bernhard Maschke and Olav Egeland

Functional Adaptive Control Simon G. Fabri and Visakan Kadirkamanathan

Algebraic Methods for Nonlinear Control Systems (Second edition) Giuseppe Conte, Claude H. Moog and Anna Maria Perdon

Positive 1D and 2D Systems Tadeusz Kaczorek

Polynomial and Rational Matrices Tadeusz Kaczorek

Identification and Control Using Volterra Models Francis J. Doyle III, Ronald K. Pearson and Bobatunde A. Ogunnaike

Hyeong Soo Chang, Michael C. Fu, Jiaqiao Hu and Steven I. Marcus

Simulation-based Algorithms for Markov Decision Processes

123

Hyeong Soo Chang Department of Computer Science and Engineering Sogang University Seoul 121-742 Republic of Korea Jiaqiao Hu Department of Applied Mathematics and Statistics State University of New York at Stony Brook Stony Brook NY 11794 USA

Michael C. Fu Smith School of Business and Institute for Systems Research University of Maryland College Park MD 20742 USA Steven I. Marcus Department of Electrical and Computer Engineering and Institute for Systems Research University of Maryland College Park MD 20742 USA

British Library Cataloguing in Publication Data Simulation-based algorithms for Markov decision processes. - (Communications and control engineering) 1. Decision making - Mathematica