---
title: "Symbol Acquisition for Probabilistic High-Level Planning"
authors:
  - "George Dimitri Konidaris"
  - "Leslie Pack Kaelbling"
  - "Tomás Lozano-Pérez"
doi: ""
url: "https://ijcai.org/proceedings/2015/509"
pdf: "https://ijcai.org/proceedings/2015/0509.pdf"
venue: "Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence"
year: 2015
pages: "3619-3626"
track: "Special Track on Machine Learning"
keywords:
---

# Symbol Acquisition for Probabilistic High-Level Planning

George Dimitri Konidaris, Leslie Pack Kaelbling, Tomás Lozano-Pérez

*Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence*, pages 3619-3626.

## Abstract

We introduce a framework that enables an agent to autonomously learn its own symbolic representation of a low-level, continuous environment. Propositional symbols are formalized as names for probability distributions, providing a natural means of dealing with uncertain representations and probabilistic plans. We determine the symbols that are sufficient for computing the probability with which a plan will succeed, and demonstrate the acquisition of a symbolic representation in a computer game domain.