This book examines Gaussian processes in both model-based reinforcement learning (RL) and inference in nonlinear dynamic systems.First, we introduce PILCO, a fully Bayesian approach for efficient RL in continuous-valued state and action spaces when no expert knowledge is available. PILCO takes model uncertainties consistently into account during long-term planning to reduce model bias. Second, we propose principled algorithms for robust filtering and smoothing in GP dynamic systems.

This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time. Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program behaviors for every situation that may be encountered. For robots to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes and could solve the problems of learning and adaptation on robots. This book identifies four key challenges that must be addressed for an RL algorithm to be practical for robotic control tasks. These RL for Robotics Challenges are: 1) it must learn in very few samples; 2) it must learn in domains with continuous state features; 3) it must handle sensor and/or actuator delays; and 4) it should continually select actions in real time. This book focuses on addressing all four of these challenges. In particular, this book is focused on time-constrained domains where the first challenge is critically important. In these domains, the agent’s lifetime is not long enough for it to explore the domains thoroughly, and it must learn in very few samples.

A probabilistic reinforcement learning algorithm is presented for finding control policies in continuous state and action spaces without a prior knowledge of the dynamics. The objective of this algorithm is to learn from minimal amount of interaction with the environment in order to maximize a notion of reward, i.e. a numerical measure of the quality of the resulting state trajectories. Experience from the interactions are used to construct a set of probabilistic Gaussian process (GP) models that predict the resulting state trajectories and the reward from executing a policy on the system. These predictions are used with a technique known as Bayesian optimization to search for policies that promise higher rewards. As more experience is gathered, predictions are made with more confidence and the search for better policies relies less on new interactions with the environment.The computational demand of a GP makes it eventually impractical to use as the number of observations from interacting with the environment increase. Moreover, using a single GP to model different regions that may exhibit disparate behaviors can produce unsatisfactory representations and predictions. One way of mitigating these issues is by partitioning the observation points into different regions each represented by a local GP. With the sequential arrival of the observation points from new experiences, it is necessary to have an adaptive clustering method that can partition the data into an appropriate number of regions. This led to the development of EM + algorithm presented in the second part of this work, which is an extension to the Expectation Maximization (EM) for the Gaussian mixture models, that assumes no prior knowledge of the number of components.Lastly, an application of the EM+ algorithm to filtering problems is presented. We propose a filtering algorithm that combines the advantages of the well-known particle filter and the mixture of Gaussian filter, while avoiding their issues.

A comprehensive and self-contained introduction to Gaussian processes, which provide a principled, practical, probabilistic approach to learning in kernel machines. Gaussian processes (GPs) provide a principled, practical, probabilistic approach to learning in kernel machines. GPs have received increased attention in the machine-learning community over the past decade, and this book provides a long-needed systematic and unified treatment of theoretical and practical aspects of GPs in machine learning. The treatment is comprehensive and self-contained, targeted at researchers and students in machine learning and applied statistics. The book deals with the supervised-learning problem for both regression and classification, and includes detailed algorithms. A wide variety of covariance (kernel) functions are presented and their properties discussed. Model selection is discussed both from a Bayesian and a classical perspective. Many connections to other well-known techniques from machine learning and statistics are discussed, including support-vector machines, neural networks, splines, regularization networks, relevance vector machines and others. Theoretical issues including learning curves and the PAC-Bayesian framework are treated, and several approximation methods for learning with large datasets are discussed. The book contains illustrative examples and exercises, and code and datasets are available on the Web. Appendixes provide mathematical background and a discussion of Gaussian Markov processes.

Bayesian methods for machine learning have been widely investigated, yielding principled methods for incorporating prior information into inference algorithms. This monograph provides the reader with an in-depth review of the role of Bayesian methods for the reinforcement learning (RL) paradigm. The major incentives for incorporating Bayesian reasoning in RL are that it provides an elegant approach to action-selection (exploration/exploitation) as a function of the uncertainty in learning, and it provides a machinery to incorporate prior knowledge into the algorithms. Bayesian Reinforcement Learning: A Survey first discusses models and methods for Bayesian inference in the simple single-step Bandit model. It then reviews the extensive recent literature on Bayesian methods for model-based RL, where prior information can be expressed on the parameters of the Markov model. It also presents Bayesian methods for model-free RL, where priors are expressed over the value function or policy class. Bayesian Reinforcement Learning: A Survey is a comprehensive reference for students and researchers with an interest in Bayesian RL algorithms and their theoretical and empirical properties.

A statistical view of uncertainty in expert systems. Knowledge, decision making, and uncertainty. Conceptual clustering and its relation to numerical taxonomy. Learning rates in supervised and unsupervised intelligent systems. Pinpoint good hypotheses with heuristics. Artificial intelligence approaches in statistics. REX review. Representing statistical computations: toward a deeper understanding. Student phase 1: a report on work in progress. Representing statistical knowledge for expert data analysis systems. Environments for supporting statistical strategy. Use of psychometric tools for knowledge acquisition: a case study. The analysis phase in development of knowledge based systems. Implementation and study of statistical strategy. Patterns in statisticalstrategy. A DIY guide to statistical strategy. An alphabet for statistician's expert systems.