Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations

Finale Doshi-Velez, George Konidaris
2016 IJCAI International Joint Conference on Artificial Intelligence  
Control applications often feature tasks with similar, but not identical, dynamics. We introduce the Hidden Parameter Markov Decision Process (HiP-MDP), a framework that parametrizes a family of related dynamical systems with a low-dimensional set of latent factors, and introduce a semiparametric regression approach for learning its structure from data. We show that a learned HiP-MDP rapidly identifies the dynamics of new task instances in several settings, flexibly adapting to task variation.
pmid:28603402 pmcid:PMC5466173 fatcat:2qn7zqtkzrepnpfhy5q3iwh3ee