On the Hardness of Finding Symmetries in Markov Decision Processes
Abstract
In this work we address the question of finding symmetries of a given MDP. We show that the problem is Isomorphism Complete , that is, the problem is polynomially equivalent to verifying whether two graphs are isomorphic. Apart from the theoretical importance of this result it has an important practical application. The reduction presented can be used together with any off-the-shelf Graph Isomorphism solver, which performs well in the average case, to find symmetries of an MDP. In fact, we present results of using NAutY (the best Graph Isomorphism solver currently available), to find symmetries of MDPs.
Cite
Text
Narayanamurthy and Ravindran. "On the Hardness of Finding Symmetries in Markov Decision Processes." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390243Markdown
[Narayanamurthy and Ravindran. "On the Hardness of Finding Symmetries in Markov Decision Processes." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/narayanamurthy2008icml-hardness/) doi:10.1145/1390156.1390243BibTeX
@inproceedings{narayanamurthy2008icml-hardness,
title = {{On the Hardness of Finding Symmetries in Markov Decision Processes}},
author = {Narayanamurthy, Shravan Matthur and Ravindran, Balaraman},
booktitle = {International Conference on Machine Learning},
year = {2008},
pages = {688-695},
doi = {10.1145/1390156.1390243},
url = {https://mlanthology.org/icml/2008/narayanamurthy2008icml-hardness/}
}