Probabilistic Knowledge-Based Programs
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1594-1599.
Abstract
We introduce Probabilistic Knowledge-Based Programs (PKBPs), a new, compact representation of policies for factored partially observable Markov decision processes. PKBPs use branching conditions such as if the probability of Φ is larger than p, and many more. While similar in spirit to value-based policies, PKBPs leverage the factored representation for more compactness. They also cope with more general goals than standard state-based rewards, such as pure information-gathering goals. Compactness comes at the price of reactivity, since evaluating branching conditions on-line is not polynomial in general. In this sense, PKBPs are complementary to other representations. Our intended application is as a tool for experts to specify policies in a natural, compact language, then have them verified automatically. We study succinctness and the complexity of verification for PKBPs.
@inproceedings{ijcai2015p228,
title = {Probabilistic Knowledge-Based Programs},
author = {Lang, Jérôme and Zanuttini, Bruno},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {1594--1599},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/228},
}
TY - CPAPER TI - Probabilistic Knowledge-Based Programs AU - Lang, Jérôme AU - Zanuttini, Bruno T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 1594 EP - 1599 UR - https://ijcai.org/proceedings/2015/228 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
