Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. While these methods have had experimental successes and have been shown to exhibit some desirable properties in theory, the basic learning algorithms have often been found slow in practice. Therefore, much of the current RL research focuses on speeding up learning by taking advantage of domain knowledge, or by better utilizing agents' experience. The ambitious goal of transfer learning, when applied to RL tasks, is to accelerate learning on some target task after training on a different, but related, source task. This dissertation demonstrates that transfer learning methods can successfully improve learning in RL tasks via experience from previously learned tasks. Transfer learning can increase RL's applicability to difficult tasks by allowing agents to generalize their experience across learning problems. This dissertation presents inter-task mappings, the first transfer mechanism in this area to successfully enable transfer between tasks with different state variables and actions. Inter-task mappings have subsequently been used by a number of transfer researchers. A set of six transfer learning algorithms are then introduced. While these transfer methods differ in terms of what base RL algorithms they are compatible with, what type of knowledge they transfer, and what their strengths are, all utilize the same inter-task mapping mechanism. These transfer methods can all successfully use mappings constructed by a human from domain knowledge, but there may be situations in which domain knowledge is unavailable, or insufficient, to describe how two given tasks are related. We therefore also study how inter-task mappings can be learned autonomously by leveraging existing machine learning algorithms. Our methods use classification and regression techniques to successfully discover similarities between data gathered in pairs of tasks, culminating in what is currently one of the most robust mapping-learning algorithms for RL transfer. Combining transfer methods with these similarity-learning algorithms allows us to empirically demonstrate the plausibility of autonomous transfer. We fully implement these methods in four domains (each with different salient characteristics), show that transfer can significantly improve an agent's ability to learn in each domain, and explore the limits of transfer's applicability.

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently begun to investigate the benefits of transferring knowledge. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research. The key contributions of this book are: Definition of the transfer problem in RL domains Background on RL, sufficient to allow a wide audience to understand discussed transfer concepts Taxonomy for transfer methods in RL Survey of existing approaches In-depth presentation of selected transfer methods Discussion of key open questions By way of the research presented in this book, the author has established himself as the pre-eminent worldwide expert on transfer learning in sequential decision making tasks. A particular strength of the research is its very thorough and methodical empirical evaluation, which Matthew presents, motivates, and analyzes clearly in prose throughout the book. Whether this is your initial introduction to the concept of transfer learning, or whether you are a practitioner in the field looking for nuanced details, I trust that you will find this book to be an enjoyable and enlightening read. Peter Stone, Associate Professor of Computer Science

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently begun to investigate the benefits of transferring knowledge. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research. The key contributions of this book are: Definition of the transfer problem in RL domains Background on RL, sufficient to allow a wide audience to understand discussed transfer concepts Taxonomy for transfer methods in RL Survey of existing approaches In-depth presentation of selected transfer methods Discussion of key open questions By way of the research presented in this book, the author has established himself as the pre-eminent worldwide expert on transfer learning in sequential decision making tasks. A particular strength of the research is its very thorough and methodical empirical evaluation, which Matthew presents, motivates, and analyzes clearly in prose throughout the book. Whether this is your initial introduction to the concept of transfer learning, or whether you are a practitioner in the field looking for nuanced details, I trust that you will find this book to be an enjoyable and enlightening read. Peter Stone, Associate Professor of Computer Science

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.

Learning to solve sequential decision-making tasks is difficult. Humans take years exploring the environment essentially in a random way until they are able to reason, solve difficult tasks, and collaborate with other humans towards a common goal. Artificial Intelligent agents are like humans in this aspect. Reinforcement Learning (RL) is a well-known technique to train autonomous agents through interactions with the environment. Unfortunately, the learning process has a high sample complexity to infer an effective actuation policy, especially when multiple agents are simultaneously actuating in the environment. However, previous knowledge can be leveraged to accelerate learning and enable solving harder tasks. In the same way humans build skills and reuse them by relating different tasks, RL agents might reuse knowledge from previously solved tasks and from the exchange of knowledge with other agents in the environment. In fact, virtually all of the most challenging tasks currently solved by RL rely on embedded knowledge reuse techniques, such as Imitation Learning, Learning from Demonstration, and Curriculum Learning. This book surveys the literature on knowledge reuse in multiagent RL. The authors define a unifying taxonomy of state-of-the-art solutions for reusing knowledge, providing a comprehensive discussion of recent progress in the area. In this book, readers will find a comprehensive discussion of the many ways in which knowledge can be reused in multiagent sequential decision-making tasks, as well as in which scenarios each of the approaches is more efficient. The authors also provide their view of the current low-hanging fruit developments of the area, as well as the still-open big questions that could result in breakthrough developments. Finally, the book provides resources to researchers who intend to join this area or leverage those techniques, including a list of conferences, journals, and implementation tools. This book will be useful for a wide audience; and will hopefully promote new dialogues across communities and novel developments in the area.

This book constitutes the refereed proceedings of the joint conference on Machine Learning and Knowledge Discovery in Databases: ECML PKDD 2008, held in Antwerp, Belgium, in September 2008. The 100 papers presented in two volumes, together with 5 invited talks, were carefully reviewed and selected from 521 submissions. In addition to the regular papers the volume contains 14 abstracts of papers appearing in full version in the Machine Learning Journal and the Knowledge Discovery and Databases Journal of Springer. The conference intends to provide an international forum for the discussion of the latest high quality research results in all areas related to machine learning and knowledge discovery in databases. The topics addressed are application of machine learning and data mining methods to real-world problems, particularly exploratory research that describes novel learning and mining tasks and applications requiring non-standard techniques.

This book constitutes the refereed proceedings of the 10th International Conference on Scalable Uncertainty Management, SUM 2016, held in Nice, France, in September 2016. The 18 regular papers and 5 short papers were carefully reviewed and selected from 35 submissions. Papers are solicited in all areas of managing and reasoning with substantial and complex kinds of uncertain, incomplete or inconsistent information. These include (but are not restricted to) applications in decision support systems, risk analysis, machine learning, belief networks, logics of uncertainty, belief revision and update, argumentation, negotiation technologies, semantic web applications, search engines, ontology systems, information fusion, information retrieval, natural language processing, information extraction, image recognition, vision systems, data and text mining, and the consideration of issues such as provenance, trust, heterogeneity, and complexity of data and knowledge.