The Markov Assumption: Formalization and Impact
Abstract
We provide both a semantic interpretation and logical (inferential) characterization of the Markov principle that underlies the main action theories in AI. This principle will be shown to constitute a nonmonotonic assumption that justifies the actual restrictions on action descriptions in these theories, as well as constraints on allowable queries. It will be shown also that the well-known regression principle is a consequence of the Markov assumption, and it is valid also for non-deterministic domains.
Cite
Text
Bochman. "The Markov Assumption: Formalization and Impact." International Joint Conference on Artificial Intelligence, 2013.Markdown
[Bochman. "The Markov Assumption: Formalization and Impact." International Joint Conference on Artificial Intelligence, 2013.](https://mlanthology.org/ijcai/2013/bochman2013ijcai-markov/)BibTeX
@inproceedings{bochman2013ijcai-markov,
title = {{The Markov Assumption: Formalization and Impact}},
author = {Bochman, Alexander},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2013},
pages = {782-788},
url = {https://mlanthology.org/ijcai/2013/bochman2013ijcai-markov/}
}