Symbol Acquisition for Probabilistic High-Level Planning
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.
Cite
Text
Konidaris et al. "Symbol Acquisition for Probabilistic High-Level Planning." International Joint Conference on Artificial Intelligence, 2015.Markdown
[Konidaris et al. "Symbol Acquisition for Probabilistic High-Level Planning." International Joint Conference on Artificial Intelligence, 2015.](https://mlanthology.org/ijcai/2015/konidaris2015ijcai-symbol/)BibTeX
@inproceedings{konidaris2015ijcai-symbol,
title = {{Symbol Acquisition for Probabilistic High-Level Planning}},
author = {Konidaris, George Dimitri and Kaelbling, Leslie Pack and Lozano-Pérez, Tomás},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2015},
pages = {3619-3627},
url = {https://mlanthology.org/ijcai/2015/konidaris2015ijcai-symbol/}
}