@inproceedings{a15d05e392d5479db468a37f125612ce,
title = "Learning and solving regular decision processes",
abstract = "Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distribution and an expected reward for each state-action pair. Building on this representation, we combine automata learning techniques with history clustering to learn such a Mealy Machine and solve it by adapting MCTS to it. We empirically evaluate this approach, demonstrating its feasibility.",
author = "Eden Abadi and Brafman, {Ronen I.}",
note = "Funding Information: We thank Dr. Bo Zhang for providing reagents and stimulating discussions. Thank Ms. Xuehong Liang for technical assistance. This work was supported by the grants from NSFC (Nos. 31201007 and 31100889) and the 973 grant 2012CB825504. Publisher Copyright: {\textcopyright} 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.; 29th International Joint Conference on Artificial Intelligence, IJCAI 2020 ; Conference date: 01-01-2021",
year = "2020",
month = jan,
day = "1",
language = "American English",
series = "IJCAI International Joint Conference on Artificial Intelligence",
pages = "1948--1954",
editor = "Christian Bessiere",
booktitle = "Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020",
}