Partially Observed Markov Decision Processes

Vikram Krishnamurthy is Professor of Electrical and Computer Engineering at Cornell University. From 2002 to 2016, he was Professor and Senior Canada Research Chair in Statistical Signal Processing at the University of British Columbia. His research contributions are in statistical signal processing, stochastic optimization and control, with applications in social networks, adaptive radar systems and biological ion channels. He is a Fellow of IEEE and served as Distinguished Lecturer for the IEEE Signal Processing Society and Editor-in-Chief of IEEE Journal of Selected Topics in Signal Processing. He was awarded an honorary doctorate from the Royal Institute of Technology (KTH) Sweden in 2014.

• Preface to revised edition; Notation; 1. Introduction; I. Stochastic Models and Bayesian Filtering: 2. Stochastic state space model; 3. Optimal filtering; 4. Algorithms for maximum likelihood parameter estimation; 5. Multi-agent sensing: social learning and data incest; 6. Nonparametric Bayesian inference; II. POMDPs: Models and Applications: 7. Fully observed Markov decision processes; 8. Partially observed Markov decision processes; 9. POMDPs in controlled sensing and sensor scheduling; III. POMDP Structural Results: 10. Structural results for Markov decision processes; 11. Structural results for optimal filters; 12. Monotonicity of value function for POMDPs; 13. Structural results for stopping-time POMDPs; 14. Stopping-Time POMDPs for quickest detection; 15. Myopic policy bounds for POMDPs and sensitivity to model parameters; IV. Stochastic Gradient Algorithms and Reinforcement Learning: 16. Stochastic optimization and gradient estimation; 17. Reinforcement learning; 18. Stochastic gradient algorithms: convergence analysis; 19. Discrete stochastic optimization; V. Inverse Reinforcement Learning: 20. Revealed preferences for inverse reinforcement learning; 21. Bayesian inverse reinforcement learning; Appendix A. Short primer on stochastic stimulation; Appendix B. Continuous-time HMM filters; Appendix C. Discrete-time Martingales; Appendix D. Markov processes; Appendix E. Some limit theorems in statistics; Appendix F. Summary of POMDP algorithms; Bibliography; Index.

'This book uniquely offers a comprehensive treatment of structural results for Partially Observable Markov Decision Processes (POMDPs), utilizing submodularity and stochastic orders. The new edition expands its scope by introducing essential results in nonparametric Bayes, stochastic optimization, and inverse reinforcement learning, making it an invaluable resource as both a textbook and reference.' Bo Wahlberg, KTH Royal Institute of Technology, Sweden