Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision problems under uncertainty as well as Reinforcement Learning problems.
Written by experts in the field, this book provides a global view of current research using MDPs in Artificial Intelligence. It starts with an introductory presentation of the fundamental aspects of MDPs (planning in MDPs, Reinforcement Learning, Partially Observable MDPs, Markov games and the use of non-classical criteria). Then it presents more advanced research trends in the domain and gives some concrete examples using illustrative applications.
Part 1. MDPs: Models and Methods
1. Markov Decision Processes, F. Garcia, E. Rachelson.
2. Reinforcement Learning, O. Sigaud, F. Garcia.
3. Approximate Dynamic Programming, R. Munos.
4. Factored Markov Decision Processes, T. Degris, O. Sigaud.
5. Policy-gradient Algorithms, O. Buffet.
6. Online Resolution Techniques, L. Péret, F. Garcia.
Part 2. Beyond MDPs
7. Partially Observable Markov Decision Processes, A. Dutech, B. Scherrer.
8. Stochastic Games, A. Burkov, L. Matignon, B. Chaib-Draa.
9. DEC-MDP/ POMDP, A. Beynier et al.
10. Non-standard Criteria, M. Boussard, M. Bouzid, A.-I. Mouaddib, R. Sabbadin, P. Weng.
Part 3. Applications
11. Online Learning for Micro-object Manipulation, G. Laurent.
12. Conservation of Biodiversity Conservation, I. Chadès.
13. Autonomous Helicopter Searching for a Landing Area in an Uncertain Environment, P. Fabiani, F. Teichteil-Königsbuch.
14. Resource Consumption Control for an Autonomous Robot, S. Le Gloannec, A.-I. Mouaddib.
15. Operations Planning, S. Thiébaux, O. Buffet.
Olivier Sigaud is a Professor of Computer Science at the University of Paris 6 (UPMC). He is the Head of the "Motion" Group in the Institute of Intelligent Systems and Robotics (ISIR).
Olivier Buffet has been an INRIA researcher in the Autonomous Intelligent Machines (MAIA) team of the LORIA laboratory since November 2007.