Symbol acquisition for probabilistic high-level planning
Author(s)Konidaris, George; Kaelbling, Leslie P; Lozano-Perez, Tomas
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
24th International Joint Conference on Artificial Intelligence (IJCAI 2015)
AAAI Press / International Joint Conferences on Artificial Intelligence
Konidaris, George et al. "Symbol Acquisition for Probabilistic High-Level Planning" Proceedings of the Twenty Fourth International Joint Conference on Artificial Intelligence (IJCAI),Buenos Aires, Argentina, AAAI Press / International Joint Conferences on Artificial Intelligence, 2015.
Author's final manuscript