Computational Approaches for Stochastic Shortest Path on Succinct MDPs
Abstract
We consider the stochastic shortest path (SSP) problem for succinct Markov decision processes (MDPs), where the MDP consists of a set of variables, and a set of nondeterministic rules that update the variables. First, we show that several examples from the AI literature can be modeled as succinct MDPs. Then we present computational approaches for upper and lower bounds for the SSP problem: (a) for computing upper bounds, our method is polynomial-time in the implicit description of the MDP; (b) for lower bounds, we present a polynomial-time (in the size of the implicit description) reduction to quadratic programming. Our approach is applicable even to infinite-state MDPs. Finally, we present experimental results to demonstrate the effectiveness of our approach on several classical examples from the AI literature.
Cite
Text
Chatterjee et al. "Computational Approaches for Stochastic Shortest Path on Succinct MDPs." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/653Markdown
[Chatterjee et al. "Computational Approaches for Stochastic Shortest Path on Succinct MDPs." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/chatterjee2018ijcai-computational/) doi:10.24963/IJCAI.2018/653BibTeX
@inproceedings{chatterjee2018ijcai-computational,
title = {{Computational Approaches for Stochastic Shortest Path on Succinct MDPs}},
author = {Chatterjee, Krishnendu and Fu, Hongfei and Goharshady, Amir Kafshdar and Okati, Nastaran},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {4700-4707},
doi = {10.24963/IJCAI.2018/653},
url = {https://mlanthology.org/ijcai/2018/chatterjee2018ijcai-computational/}
}