Symbol acquisition for probabilistic high-level planning
Publication
, Conference
Konidaris, G; Kaelbling, LP; Lozano-Perez, T
Published in: IJCAI International Joint Conference on Artificial Intelligence
January 1, 2015
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.
Duke Scholars
Published In
IJCAI International Joint Conference on Artificial Intelligence
ISSN
1045-0823
ISBN
9781577357384
Publication Date
January 1, 2015
Volume
2015-January
Start / End Page
3619 / 3627
Citation
APA
Chicago
ICMJE
MLA
NLM
Konidaris, G., Kaelbling, L. P., & Lozano-Perez, T. (2015). Symbol acquisition for probabilistic high-level planning. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 2015-January, pp. 3619–3627).
Konidaris, G., L. P. Kaelbling, and T. Lozano-Perez. “Symbol acquisition for probabilistic high-level planning.” In IJCAI International Joint Conference on Artificial Intelligence, 2015-January:3619–27, 2015.
Konidaris G, Kaelbling LP, Lozano-Perez T. Symbol acquisition for probabilistic high-level planning. In: IJCAI International Joint Conference on Artificial Intelligence. 2015. p. 3619–27.
Konidaris, G., et al. “Symbol acquisition for probabilistic high-level planning.” IJCAI International Joint Conference on Artificial Intelligence, vol. 2015-January, 2015, pp. 3619–27.
Konidaris G, Kaelbling LP, Lozano-Perez T. Symbol acquisition for probabilistic high-level planning. IJCAI International Joint Conference on Artificial Intelligence. 2015. p. 3619–3627.
Published In
IJCAI International Joint Conference on Artificial Intelligence
ISSN
1045-0823
ISBN
9781577357384
Publication Date
January 1, 2015
Volume
2015-January
Start / End Page
3619 / 3627