How to Dynamically Merge Markov Decision Processes
Abstract
We are frequently called upon to perform multiple tasks that com(cid:173) pete for our attention and resource. Often we know the optimal solution to each task in isolation; in this paper, we describe how this knowledge can be exploited to efficiently find good solutions for doing the tasks in parallel. We formulate this problem as that of dynamically merging multiple Markov decision processes (MDPs) into a composite MDP, and present a new theoretically-sound dy(cid:173) namic programming algorithm for finding an optimal policy for the composite MDP. We analyze various aspects of our algorithm and illustrate its use on a simple merging problem.
Cite
Text
Singh and Cohn. "How to Dynamically Merge Markov Decision Processes." Neural Information Processing Systems, 1997.Markdown
[Singh and Cohn. "How to Dynamically Merge Markov Decision Processes." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/singh1997neurips-dynamically/)BibTeX
@inproceedings{singh1997neurips-dynamically,
title = {{How to Dynamically Merge Markov Decision Processes}},
author = {Singh, Satinder P. and Cohn, David},
booktitle = {Neural Information Processing Systems},
year = {1997},
pages = {1057-1063},
url = {https://mlanthology.org/neurips/1997/singh1997neurips-dynamically/}
}