In this thesis decision-making problems are formalized using a stochastic discrete-time model called decentralized partially observable Markov decision process (Dec-POMDP).

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.

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 three-volume set LNAI 8188, 8189 and 8190 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2013, held in Prague, Czech Republic, in September 2013. The 111 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 447 submissions. The papers are organized in topical sections on reinforcement learning; Markov decision processes; active learning and optimization; learning from sequences; time series and spatio-temporal data; data streams; graphs and networks; social network analysis; natural language processing and information extraction; ranking and recommender systems; matrix and tensor analysis; structured output prediction, multi-label and multi-task learning; transfer learning; bayesian learning; graphical models; nearest-neighbor methods; ensembles; statistical learning; semi-supervised learning; unsupervised learning; subgroup discovery, outlier detection and anomaly detection; privacy and security; evaluation; applications; and medical applications.

Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can often increase the efficacy of the treatment, but at the cost of more severe side effects. In this book, we outline how to deal with multiple objectives in decision-theoretic planning and reinforcement learning algorithms. To illustrate this, we employ the popular problem classes of multi-objective Markov decision processes (MOMDPs) and multi-objective coordination graphs (MO-CoGs). First, we discuss different use cases for multi-objective decision making, and why they often necessitate explicitly multi-objective algorithms. We advocate a utility-based approach to multi-objective decision making, i.e., that what constitutes an optimal solution to a multi-objective decision problem should be derived from the available information about user utility. We show how different assumptions about user utility and what types of policies are allowed lead to different solution concepts, which we outline in a taxonomy of multi-objective decision problems. Second, we show how to create new methods for multi-objective decision making using existing single-objective methods as a basis. Focusing on planning, we describe two ways to creating multi-objective algorithms: in the inner loop approach, the inner workings of a single-objective method are adapted to work with multi-objective solution concepts; in the outer loop approach, a wrapper is created around a single-objective method that solves the multi-objective problem as a series of single-objective problems. After discussing the creation of such methods for the planning setting, we discuss how these approaches apply to the learning setting. Next, we discuss three promising application domains for multi-objective decision making algorithms: energy, health, and infrastructure and transportation. Finally, we conclude by outlining important open problems and promising future directions.

This compendium covers several important topics related to multiagent systems, from learning and game theoretic analysis, to automated negotiation and human-agent interaction. Each chapter is written by experienced researchers working on a specific topic in mutliagent system interactions, and covers the state-of-the-art research results related to that topic.The book will be a good reference material for researchers and graduate students working in the area of artificial intelligence/machine learning, and an inspirational read for those in social science, behavioural economics and psychology.

This book includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Computing Sciences, Software Engineering and Systems. The book presents selected papers from the conference proceedings of the International Conference on Systems, Computing Sciences and Software Engineering (SCSS 2006). All aspects of the conference were managed on-line.

The two-volume set LNCS 4131 and LNCS 4132 constitutes the refereed proceedings of the 16th International Conference on Artificial Neural Networks, ICANN 2006. The set presents 208 revised full papers, carefully reviewed and selected from 475 submissions. This first volume presents 103 papers, organized in topical sections on feature selection and dimension reduction for regression, learning algorithms, advances in neural network learning methods, ensemble learning, hybrid architectures, and more.

This book constitutes the refereed proceedings of the 19th Brazilian Symposium on Artificial Intelligence, SBIA 2008, held in Salvador, Brazil, in October 2008. The 27 revised full papers presented together with 3 invited lectures and 3 tutorials were carefully reviewed and selected from 142 submissions. The papers are organized in topical sections on computer vision and pattern recognition, distributed AI: autonomous agents, multi-agent systems and game knowledge representation and reasoning, machine learning and data mining, natural language processing, and robotics.