TY - GEN
T1 - Regular decision processes
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
AU - Brafman, Ronen I.
AU - De Giacomo, Giuseppe
N1 - Publisher Copyright: © 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - We introduce and study Regular Decision Processes (RDPs), a new, compact, factored model for domains with non-Markovian dynamics and rewards. In RDPs, transition and reward functions are specified using formulas in linear dynamic logic over finite traces, a language with the expressive power of regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and provides a model that generalizes MDPs and k-order MDPs. RDPs can also approximate POMDPs without having to postulate the existence of hidden variables, and, in principle, can be learned from observations only.
AB - We introduce and study Regular Decision Processes (RDPs), a new, compact, factored model for domains with non-Markovian dynamics and rewards. In RDPs, transition and reward functions are specified using formulas in linear dynamic logic over finite traces, a language with the expressive power of regular expressions. This allows specifying complex dependence on the past using intuitive and compact formulas, and provides a model that generalizes MDPs and k-order MDPs. RDPs can also approximate POMDPs without having to postulate the existence of hidden variables, and, in principle, can be learned from observations only.
UR - http://www.scopus.com/inward/record.url?scp=85074913237&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/766
DO - 10.24963/ijcai.2019/766
M3 - Conference contribution
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 5516
EP - 5522
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
Y2 - 10 August 2019 through 16 August 2019
ER -