---
title: "Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations"
authors:
  - "Finale Doshi-Velez"
  - "George Dimitri Konidaris"
doi: ""
url: "https://ijcai.org/proceedings/2016/206"
pdf: "https://ijcai.org/proceedings/2016/0206.pdf"
venue: "Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence"
year: 2016
pages: "1432-1439"
track: ""
keywords:
---

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

Finale Doshi-Velez, George Dimitri Konidaris

*Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence*, pages 1432-1439.

## Abstract

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.