Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis
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.
Cite
Text
Lizotte et al. "Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis." International Conference on Machine Learning, 2010.Markdown
[Lizotte et al. "Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis." International Conference on Machine Learning, 2010.](https://mlanthology.org/icml/2010/lizotte2010icml-efficient/)BibTeX
@inproceedings{lizotte2010icml-efficient,
title = {{Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis}},
author = {Lizotte, Daniel J. and Bowling, Michael H. and Murphy, Susan A.},
booktitle = {International Conference on Machine Learning},
year = {2010},
pages = {695-702},
url = {https://mlanthology.org/icml/2010/lizotte2010icml-efficient/}
}