Thomas Dean
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Thomas Dean has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Craig Boutilier
Dept. of Computer Science University of British Columbia Vancouver V6T 1Z4 BC
1 shared publication - Dana Angluin
Yale University
1 shared publication Evangelos Kokkevis
Brown University
1 shared publication- Kenneth Basye
Brown University
1 shared publication - Leslie Pack Kaelbling
Brown University
1 shared publication - Oded Maron
Brown University
1 shared publication
Latest Publications
- Open Access
Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives adopted in these areas often differ in substantial ways, many planning problems of interest to researchers in these fields can be modeled as Markov decision processes (MDPs) and analyzed using the techniques of decision theory. This paper presents an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI. It also describes structural properties of MDPs that, when exhibited by particular classes of problems, can be exploited in the construction of optimal or approximately optimal policies or plans. Planning problems commonly possess structure in the reward and value functions used to describe performance criteria, in the functions used to describe state transitions and observations, and in the relationships among features used to describe states, actions, rewards, and observations. Specialized representations, and algorithms employing these representations, can achieve computational leverage by exploiting these various forms of structure. Certain AI techniques -- in particular those based on the use of structured, intensional representations -- can be viewed in this way. This paper surveys several types of representations for both classical and decision-theoretic planning problems, and planning algorithms that exploit these representations in a number of different ways to ease the computational burden of constructing policies or plans. It focuses primarily on abstraction, aggregation and decomposition techniques based on AI-style representations.
Open AccessDecision-Theoretic Planning: Structural Assumptions and Computational Leverage
Planning under uncertainty is a central problem in the study of automated sequential decision making, and has been addressed by researchers in many different fields, including AI planning, decision analysis, operations research, control theory and economics. While the assumptions and perspectives adopted in these areas often differ in substantial ways, many planning problems of interest to researchers in these fields can be modeled as Markov decision processes (MDPs) and analyzed using the techniques of decision theory. This paper presents an overview and synthesis of MDP-related methods, showing how they provide a unifying framework for modeling many classes of planning problems studied in AI. It also describes structural properties of MDPs that, when exhibited by particular classes of problems, can be exploited in the construction of optimal or approximately optimal policies or plans. Planning problems commonly possess structure in the reward and value functions used to describe performance criteria, in the functions used to describe state transitions and observations, and in the relationships among features used to describe states, actions, rewards, and observations. Specialized representations, and algorithms employing these representations, can achieve computational leverage by exploiting these various forms of structure. Certain AI techniques -- in particular those based on the use of structured, intensional representations -- can be viewed in this way. This paper surveys several types of representations for both classical and decision-theoretic planning problems, and planning algorithms that exploit these representations in a number of different ways to ease the computational burden of constructing policies or plans. It focuses primarily on abstraction, aggregation and decomposition techniques based on AI-style representations.
- 30 January 2007
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 47 (3-4) , 223-250
Learning invariant features using inertial priors
- 30 January 2007
- Published by Springer Nature in Annals of Mathematics and Artificial Intelligence
- Vol. 47 (3-4) , 223-250
Learning invariant features using inertial priors
- 31 July 2003
- Published by Elsevier in Artificial Intelligence
- Vol. 147 (1-2) , 225-251
Solving factored MDPs using non-homogeneous partitions
- 31 July 2003
- Published by Elsevier in Artificial Intelligence
- Vol. 147 (1-2) , 225-251
Solving factored MDPs using non-homogeneous partitions
- 1 January 1995
- Published by Springer Nature in Machine Learning
- Vol. 18 (1) , 81-108
Inferring finite automata with stochastic output functions and an application to map learning
- 1 January 1995
- Published by Springer Nature in Machine Learning
- Vol. 18 (1) , 81-108
Inferring finite automata with stochastic output functions and an application to map learning