Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis

Daniel J. Lizotte, Michael Bowling, and Susan A. Murphy. Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis. In Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML), pp. 695–702, 2010.

Download

[PDF] 

Abstract

We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all non-dominated actions in the continuous state setting. This novel extension is appropriate for environments with continuous or finely discretized states where generalization is required, as is the case for data analysis of randomized controlled trials.

BibTeX

@InProceedings(10icml-multiplerewards,
  Title = "Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis",
  Author = "Daniel J. Lizotte and Michael Bowling and Susan A. Murphy",
  Booktitle = "Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML)",
  Year = "2010",
  pages = "695--702",
  AcceptRate = "26\%",
  AcceptNumbers = "152 of 594"
)

Generated by bib2html.pl (written by Patrick Riley) on Fri Feb 13, 2015 15:54:27