Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Model-based Bayesian Reinforcement Learning (BRL) provides a principled solution to dealing with the exploration-exploitation trade-off, but such methods typically assume a fully observable environments. The few Bayesian RL methods that are applicable in partially observable domains, such as the Bayes-Adaptive POMDP (BA-POMDP), scale poorly. To address this issue, we introduce the Factored BA-POMDP model (FBA-POMDP), a framework that is able to learn a compact model of the dynamics by exploiting the underlying structure of a POMDP. The FBA-POMDP framework casts the problem as a planning task, for which we adapt the Monte-Carlo Tree Search planning algorithm and develop a belief tracking method to approximate the joint posterior over the state and model variables. Our empirical results show that this method outperforms a number of BRL baselines and is able to learn efficiently when the factorization is known, as well as learn both the factorization and the model parameters simultaneously.

/pdf/bayesian-reinforcement-learning-in-factored-pomdps-xpra8a8w97.pdf

Bayesian Reinforcement Learning in Factored POMDPs

Matrix Factorization Techniques for Recommender Systems

This exciting and pioneering new overview of multiagent systems, which are online systems composed of multiple interacting intelligent agents, i.e., online trading, offers a newly seen computer science perspective on multiagent systems, while integrating ideas from operations research, game theory, economics, logic, and even philosophy and linguistics. The authors emphasize foundations to create a broad and rigorous treatment of their subject, with thorough presentations of distributed problem solving, game theory, multiagent communication and learning, social choice, mechanism design, auctions, cooperative game theory, and modal logics of knowledge and belief. For each topic, basic concepts are introduced, examples are given, proofs of key results are offered, and algorithmic considerations are examined. An appendix covers background material in probability theory, classical logic, Markov decision processes and mathematical programming. Written by two of the leading researchers of this engaging field, this book will surely serve as THE reference for researchers in the fastest-growing area of computer science, and be used as a text for advanced undergraduate or graduate courses.

Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations

Multiagent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, and economics. The complexity of many tasks arising in these domains makes them difficult to solve with preprogrammed agent behaviors. The agents must, instead, discover a solution on their own, using learning. A significant part of the research on multiagent learning concerns reinforcement learning techniques. This paper provides a comprehensive survey of multiagent reinforcement learning (MARL). A central issue in the field is the formal statement of the multiagent learning goal. Different viewpoints on this issue have led to the proposal of many different goals, among which two focal points can be distinguished: stability of the agents' learning dynamics, and adaptation to the changing behavior of the other agents. The MARL algorithms described in the literature aim---either explicitly or implicitly---at one of these two goals or at a combination of both, in a fully cooperative, fully competitive, or more general setting. A representative selection of these algorithms is discussed in detail in this paper, together with the specific issues that arise in each category. Additionally, the benefits and challenges of MARL are described along with some of the problem domains where the MARL techniques have been applied. Finally, an outlook for the field is provided.

/pdf/a-comprehensive-survey-of-multiagent-reinforcement-learning-1mwdfqzdug.pdf

A Comprehensive Survey of Multiagent Reinforcement Learning

We extend Q-learning to a noncooperative multiagent context, using the framework of general-sum stochastic games. A learning agent maintains Q-functions over joint actions, and performs updates based on assuming Nash equilibrium behavior over the current Q-values. This learning protocol provably converges given certain restrictions on the stage games (defined by Q-values) that arise during learning. Experiments with a pair of two-player grid games suggest that such restrictions on the game structure are not necessarily required. Stage games encountered during learning in both grid environments violate the conditions. However, learning consistently converges in the first grid game, which has a unique equilibrium Q-function, but sometimes fails to converge in the second, which has three different equilibrium Q-functions. In a comparison of offline learning performance in both games, we find agents are more likely to reach a joint optimal path with Nash Q-learning than with a single-agent Q-learning method. When at least one agent adopts Nash Q-learning, the performance of both agents is better than using single-agent Q-learning. We have also implemented an online version of Nash Q-learning that balances exploration with exploitation, yielding improved performance.

/pdf/nash-q-learning-for-general-sum-stochastic-games-3xhebtv7kv.pdf

Nash q-learning for general-sum stochastic games

In this paper, we adopt general-sum stochastic games as a framework for multiagent reinforcement learning. Our work extends previous work by Littman on zero-sum stochastic games to a broader framework. We design a multiagent Q-learning method under this framework, and prove that it converges to a Nash equilibrium under speci ed conditions. This algorithm is useful for nding the optimal strategy when there exists a unique Nash equilibrium in the game. When there exist multiple Nash equilibria in the game, this algorithm should be combined with other learning techniques to nd optimal strategies.

Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

Stroke is the third leading cause of death and the principal cause of serious long-term disability in the United States. Accurate prediction of stroke is highly valuable for early intervention and treatment. In this study, we compare the Cox proportional hazards model with a machine learning approach for stroke prediction on the Cardiovascular Health Study (CHS) dataset. Specifically, we consider the common problems of data imputation, feature selection, and prediction in medical datasets. We propose a novel automatic feature selection algorithm that selects robust features based on our proposed heuristic: conservative mean. Combined with Support Vector Machines (SVMs), our proposed feature selection algorithm achieves a greater area under the ROC curve (AUC) as compared to the Cox proportional hazards model and L1 regularized Cox feature selection algorithm. Furthermore, we present a margin-based censored regression algorithm that combines the concept of margin-based classifiers with censored regression to achieve a better concordance index than the Cox model. Overall, our approach outperforms the current state-of-the-art in both metrics of AUC and concordance index. In addition, our work has also identified potential risk factors that have not been discovered by traditional approaches. Our method can be applied to clinical prediction of other diseases, where missing data are common and risk factors are not well understood.

/pdf/an-integrated-machine-learning-approach-to-stroke-prediction-11vwi4u0yh.pdf

An integrated machine learning approach to stroke prediction

WC analyze the problem of learning about other agents in a class of dynamic multiagent systems, where performance of the primary agent depends on behavior of the others, We consider an online version of the problem, where agents must learn models of the others in the course of continual interactions. We implement various lovels of recursive model in a simulated double auction market, Our experiments show that performance of an agent can be quite sensitive to its assumptions about the policies of other agents, and (not surprisingly), when there is substantial uncertainty about the love1 of sophistication of other agents, minimizing assumptions might be the best policy.

Online learning about other agents in a dynamic multiagent system

We present a named entity recognition (NER) system for extracting product attributes and values from listing titles. Information extraction from short listing titles present a unique challenge, with the lack of informative context and grammatical structure. In this work, we combine supervised NER with bootstrapping to expand the seed list, and output normalized results. Focusing on listings from eBay's clothing and shoes categories, our bootstrapped NER system is able to identify new brands corresponding to spelling variants and typographical errors of the known brands, as well as identifying novel brands. Among the top 300 new brands predicted, our system achieves 90.33% precision. To output normalized attribute values, we explore several string comparison algorithms and found n-gram substring matching to work well in practice.

Junling Hu

Papers

Nash q-learning for general-sum stochastic games

Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm

An integrated machine learning approach to stroke prediction

Online learning about other agents in a dynamic multiagent system

Bootstrapped Named Entity Recognition for Product Attribute Extraction