Preference Planning for Markov Decision Processes

Meilun Li, Zhikun She, Andrea Turrini, Lijun Zhang

AAAI 2015 pp. 3313-3319

doi:10.1609/AAAI.V29I1.9654 /aaai/2015/li2015aaai-preference/

Abstract

The classical planning problem can be enriched with quantitative and qualitative user-defined preferences on how the system behaves on achieving the goal. In this paper, we propose the probabilistic preference planning problem for Markov decision processes, where the preferences are based on an enriched probabilistic LTL-style logic. We develop P4Solver, an SMT-based planner computing the preferred plan by reducing the problem to quadratic programming problem, which can be solved using SMT solvers such as Z3. We illustrate the framework by applying our approach on two selected case studies.

PDF AAAI Semantic Scholar

Cite

Text

Li et al. "Preference Planning for Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9654

Markdown

[Li et al. "Preference Planning for Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/li2015aaai-preference/) doi:10.1609/AAAI.V29I1.9654

BibTeX

@inproceedings{li2015aaai-preference,
  title     = {{Preference Planning for Markov Decision Processes}},
  author    = {Li, Meilun and She, Zhikun and Turrini, Andrea and Zhang, Lijun},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {3313-3319},
  doi       = {10.1609/AAAI.V29I1.9654},
  url       = {https://mlanthology.org/aaai/2015/li2015aaai-preference/}
}