A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
Learning and Solving Regular Decision Processes
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
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 indoi:10.24963/ijcai.2020/266 dblp:conf/ijcai/WalegaGKK20 fatcat:2gcvn2udzjhvzoff6hr77feuxa