Welcome to the InfoSci Platform
Reference Hub3
Inference Strategies for Solving Semi-Markov Decision Processes

Inference Strategies for Solving Semi-Markov Decision Processes

Matthew Hoffman, Nando de Freitas
Copyright: © 2012 |Pages: 15
ISBN13: 9781609601652|ISBN10: 1609601653|EISBN13: 9781609601676
DOI: 10.4018/978-1-60960-165-2.ch005
Cite Chapter Cite Chapter

MLA

Hoffman, Matthew, and Nando de Freitas. "Inference Strategies for Solving Semi-Markov Decision Processes." Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, edited by L. Enrique Sucar, et al., IGI Global, 2012, pp. 82-96. https://doi.org/10.4018/978-1-60960-165-2.ch005

APA

Hoffman, M. & de Freitas, N. (2012). Inference Strategies for Solving Semi-Markov Decision Processes. In L. Sucar, E. Morales, & J. Hoey (Eds.), Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions (pp. 82-96). IGI Global. https://doi.org/10.4018/978-1-60960-165-2.ch005

Chicago

Hoffman, Matthew, and Nando de Freitas. "Inference Strategies for Solving Semi-Markov Decision Processes." In Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, edited by L. Enrique Sucar, Eduardo F. Morales, and Jesse Hoey, 82-96. Hershey, PA: IGI Global, 2012. https://doi.org/10.4018/978-1-60960-165-2.ch005

Export Reference

Mendeley
Favorite

Abstract

Semi-Markov decision processes are used to formulate many control problems and also play a key role in hierarchical reinforcement learning. In this chapter we show how to translate the decision making problem into a form that can instead be solved by inference and learning techniques. In particular, we will establish a formal connection between planning in semi-Markov decision processes and inference in probabilistic graphical models, then build on this connection to develop an expectation maximization (EM) algorithm for policy optimization in these models.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.