Thomas G. Dietterich

Bio: Thomas G. Dietterich is an academic researcher from Oregon State University. The author has contributed to research in topics: Reinforcement learning & Markov decision process. The author has an hindex of 74, co-authored 279 publications receiving 51935 citations. Previous affiliations of Thomas G. Dietterich include University of Wyoming & Stanford University.

Efficient Exploration for Constrained MDPs.

Abstract: Given a Markov Decision Process (MDP) defined by a simulator, a designated starting state s0, and a downside risk constraint defined as the probability of reaching catastrophic states, our goal is to find a stationary deterministic policy π that with probability 1 − δ achieves a value V (s0) that is within of the value of the optimal stationary deterministic νfeasible policy, V ∗(s0), while economizing on the number of calls to the simulator. This paper presents the first PAC-SafeRL algorithm for this purpose. The algorithm extends PACRL algorithms for efficient exploration while providing guarantees that the downside constraint is satisfied. Experiments comparing our CONSTRAINEDDDV algorithm to baselines show substantial reductions in the number of simulator calls required to find a feasible policy.

Learning MDP Action Models Via Discrete Mixture Trees

Abstract: This paper addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree (context-specific dependence) models of the conditional probability distributions of the DBNs. Existing algorithms rely on standard regression tree learning methods (both propositional and relational). However, such methods presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise. This is inappropriate for many RL domains, where the stochasticity takes the form of stochastic choice over deterministic functions. This paper introduces a regression tree algorithm in which each leaf node is modeled as a finite mixture of deterministic functions. This mixture is approximated via a greedy set cover. Experiments on three challenging RL domains show that this approach finds trees that are more accurate and that are more likely to correctly identify the conditional dependencies in the DBNs based on small samples.

Evaluating Online Text Classification Algorithms for Email Prediction in TaskTracer

Abstract: paper examines how six online multiclass text classification algorithms perform in the domain of email tagging within the TaskTracer system. TaskTracer is a project-oriented user interface for the desktop knowledge worker. TaskTracer attempts to tag all documents, web pages, and email messages with the projects to which they are relevant. In previous work, we deployed an SVM email classifier to tag email messages. However, the SVM is a batch algorithm whose training time scales quadratically with the number of examples. The goal of the study reported in this paper was to select an online learning algorithm to replace this SVM classifier. We investigated Bernoulli Naive Bayes, Multinomial Naive Bayes, Transformed Weight-Normalized Complement Naive Bayes, Term Frequency - Inverse Document Frequency counts, Online Passive Aggressive algorithms, and Linear Confidence Weighted classifiers. These methods were evaluated for their online accuracy, their sensitivity to the number and frequency of classes, and their tendency to make repeated errors. The Confidence Weighted Classifier and Bernoulli Naive Bayes were found to perform the best. They behaved more stably than the other algorithms when handling the imbalanced classes and sparse features of email data.

Inferring strategies from limited reconnaissance in real-time strategy games

Abstract: In typical real-time strategy (RTS) games, enemy units are visible only when they are within sight range of a friendly unit. Knowledge of an opponent's disposition is limited to what can be observed through scouting. Information is costly, since units dedicated to scouting are unavailable for other purposes, and the enemy will resist scouting attempts. It is important to infer as much as possible about the opponent's current and future strategy from the available observations. We present a dynamic Bayes net model of strategies in the RTS game Starcraft that combines a generative model of how strategies relate to observable quantities with a principled framework for incorporating evidence gained via scouting. We demonstrate the model's ability to infer unobserved aspects of the game from realistic observations.

Anomaly Detection Meta-Analysis Benchmarks

Abstract: Benchmarks are derived from several data sets found at the UC Irvine Machine Learning Repository: https://archive.ics.uci.edu/ml/index.html

Random Forests

Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.

Gradient-based learning applied to document recognition

Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Going deeper with convolutions

Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

Deep Learning

Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Reinforcement Learning: An Introduction

Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.