---
title: "Probabilistic Knowledge-Based Programs"
authors:
  - "Jérôme Lang"
  - "Bruno Zanuttini"
doi: ""
url: "https://ijcai.org/proceedings/2015/228"
pdf: "https://ijcai.org/proceedings/2015/0228.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "1594-1599"
track: "Main Track"
keywords:
---

# Probabilistic Knowledge-Based Programs

Jérôme Lang, Bruno Zanuttini

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, 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.