T
Thomas G. Dietterich
Researcher at Oregon State University
Publications - 286
Citations - 58937
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.
Papers
More filters
Proceedings Article
Memory-Based Methods for Regression and Classification
TL;DR: The purpose of this workshop was to review the state-of-the-art in memory-based methods and to understand their relationship to "eager" and "global" learning algorithms such as batch backpropagation.
BookDOI
Abstraction, Reformulation, and Approximation
TL;DR: Die Online-Fachbuchhandlung beck-shop.de ist spezialisiert auf Fachbucher, insbesondere Recht, Steuern und Wirtschaft, wie Neuerscheinungsdienst oder Zusammenstellungen von Buchern zu Sonderpreisen.
Proceedings ArticleDOI
Learning visual dictionaries and decision lists for object recognition
Wei Zhang,Thomas G. Dietterich +1 more
TL;DR: Experiments on benchmark object recognition datasets show that the system based on the new discriminative dictionaries and BDL classifier give performance comparable or superior to the state-of-art generic object recognition approaches.
Posted Content
State Abstraction in MAXQ Hierarchical Reinforcement Learning
TL;DR: In this paper, five conditions under which state abstraction can be combined with the MAXQ value function decomposition are defined and shown experimentally that state abstraction is important for the successful application of MAXQ-Q learning.
Proceedings Article
A Divide and Conquer Approach to Learning from Prior Knowledge
Eric Chown,Thomas G. Dietterich +1 more
TL;DR: A new divide-and-conquer method is presented that analyzes the model to identify a series of smaller optimization problems whose sequential solution solves the global calibration problem.