ML Anthology

Symbolic Heuristic Search for Factored Markov Decision Processes

Zhengzhu Feng, Eric A. Hansen
AAAI 2002 pp. 455-460
doi:10.5555/777092.777164 /aaai/2002/feng2002aaai-symbolic/

Abstract

We describe a plnning algorithm that integrates two approaches to solving Markov decision processes with large state spaces. State abstraction is used to avoid evaluating states individually. Forward search from a start state, guided by an admissible heuristic, is used to avoid evaluating all states. We combine these two approaches in a novel way that exploits symbolic model-checking techniques and demonstrates their usefulness for decision-theoretic planning.

PDF AAAI Semantic Scholar

Cite

Text

Feng and Hansen. "Symbolic Heuristic Search for Factored Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2002. doi:10.5555/777092.777164

Markdown

[Feng and Hansen. "Symbolic Heuristic Search for Factored Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2002.](https://mlanthology.org/aaai/2002/feng2002aaai-symbolic/) doi:10.5555/777092.777164

BibTeX

@inproceedings{feng2002aaai-symbolic,
  title     = {{Symbolic Heuristic Search for Factored Markov Decision Processes}},
  author    = {Feng, Zhengzhu and Hansen, Eric A.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2002},
  pages     = {455-460},
  doi       = {10.5555/777092.777164},
  url       = {https://mlanthology.org/aaai/2002/feng2002aaai-symbolic/}
}