On the Complexity of Solving Markov Decision Problems. Littman, M. L., Dean, T. L., & Kaelbling, L. P.
On the Complexity of Solving Markov Decision Problems [link]Paper  abstract   bibtex   
Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving MDPs and the running time of MDP solution algorithms. We argue that, although MDPs can be solved efficiently in theory, more study is needed to reveal practical algorithms for solving large problems quickly. To encourage future research, we sketch some alternative methods of analysis that rely on the structure of MDPs.
@article{littmanComplexitySolvingMarkov2013,
  archivePrefix = {arXiv},
  eprinttype = {arxiv},
  eprint = {1302.4971},
  primaryClass = {cs},
  title = {On the {{Complexity}} of {{Solving Markov Decision Problems}}},
  url = {http://arxiv.org/abs/1302.4971},
  abstract = {Markov decision problems (MDPs) provide the foundations for a number of problems of interest to AI researchers studying automated planning and reinforcement learning. In this paper, we summarize results regarding the complexity of solving MDPs and the running time of MDP solution algorithms. We argue that, although MDPs can be solved efficiently in theory, more study is needed to reveal practical algorithms for solving large problems quickly. To encourage future research, we sketch some alternative methods of analysis that rely on the structure of MDPs.},
  urldate = {2019-01-21},
  date = {2013-02-20},
  keywords = {Computer Science - Artificial Intelligence},
  author = {Littman, Michael L. and Dean, Thomas L. and Kaelbling, Leslie Pack},
  file = {/home/dimitri/Nextcloud/Zotero/storage/R6IPHFQW/Littman et al. - 2013 - On the Complexity of Solving Markov Decision Probl.pdf;/home/dimitri/Nextcloud/Zotero/storage/7NDC6AA9/1302.html}
}

Downloads: 0