A partially observable Markov decision process (POMDP) is a mathematical framework for planning and control problems in which actions have stochastic effects and observations provide uncertain state information. It is widely used for research in decision-theoretic planning and reinforcement learning. To cope with partial observability, a policy (or plan) must use memory, and previous work has shown that a finite-state controller provides a good policy representation. This thesis considers a previously-developed bounded policy iteration algorithm for POMDPs that finds policies that take the form of stochastic finite-state controllers. Two new improvements of this algorithm are developed. First improvement provides a simplification of the basic linear program, which is used to find improved controllers. This results in a considerable speed-up in efficiency of the original algorithm. Secondly, a branch and bound algorithm for adding the best possible node to the controller is presented, which provides an error bound and a test for global optimality. Experimental results show that these enhancements significantly improve the algorithm's performance.

A partially observable Markov decision process (POMDP) is a mathematical framework for planning and control problems in which actions have stochastic effects and observations provide uncertain state information. It is widely used for research in decision-theoretic planning and reinforcement learning. % To cope with partial observability, a policy (or plan) must use memory, and previous work has shown that a finite-state controller provides a good policy representation. This thesis considers a previously-developed bounded policy iteration algorithm for POMDPs that finds policies that take the form of stochastic finite-state controllers. Two new improvements of this algorithm are developed. First improvement provides a simplification of the basic linear program, which is used to find improved controllers. This results in a considerable speed-up in efficiency of the original algorithm. Secondly, a branch and bound algorithm for adding the best possible node to the controller is presented, which provides an error bound and a test for global optimality. Experimental results show that these enhancements significantly improve the algorithm's performance.

Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement learning has progressed tremendously in the past decade. The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together they truly represent a state-of-the-art of current reinforcement learning research. Marco Wiering works at the artificial intelligence department of the University of Groningen in the Netherlands. He has published extensively on various reinforcement learning topics. Martijn van Otterlo works in the cognitive artificial intelligence group at the Radboud University Nijmegen in The Netherlands. He has mainly focused on expressive knowledge representation in reinforcement learning settings.

This book constitutes the thoroughly refereed conference proceedings of the Third International Conference on Algorithmic Decision Theory, ADT 2013, held in November 2013 in Bruxelles, Belgium. The 33 revised full papers presented were carefully selected from more than 70 submissions, covering preferences in reasoning and decision making, uncertainty and robustness in decision making, multi-criteria decision analysis and optimization, collective decision making, learning and knowledge extraction for decision support.

This book constitutes the refereed proceedings of the 6th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2001, held in Toulouse, France in September 2001. The 68 revised full papers presented together with three invited papers were carefully reviewed and selected from over a hundred submissions. The book offers topical sections on decision theory, partially observable Markov decision processes, decision-making, coherent probabilities, Bayesian networks, learning causal networks, graphical representation of uncertainty, imprecise probabilities, belief functions, fuzzy sets and rough sets, possibility theory, merging, belief revision and preferences, inconsistency handling, default logic, logic programming, etc.

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). It then presents more advanced research trends in the field and gives some concrete examples using illustrative real life applications.

This book introduces multiagent planning under uncertainty as formalized by decentralized partially observable Markov decision processes (Dec-POMDPs). The intended audience is researchers and graduate students working in the fields of artificial intelligence related to sequential decision making: reinforcement learning, decision-theoretic planning for single agents, classical multiagent planning, decentralized control, and operations research.