Learning and solving regular decision processes

Eden Abadi, Ronen I. Brafman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageAmerican English
Title of host publicationProceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
EditorsChristian Bessiere
Pages1948-1954
Number of pages7
ISBN (Electronic)9780999241165
StatePublished - 1 Jan 2020
Event29th International Joint Conference on Artificial Intelligence, IJCAI 2020 - Yokohama, Japan
Duration: 1 Jan 2021 → …

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2021-January

Conference

Conference29th International Joint Conference on Artificial Intelligence, IJCAI 2020
Country/TerritoryJapan
CityYokohama
Period1/01/21 → …

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this