A Predictive Model for Imitation Learning in Partially Observable Environments

Author

Boularias, Abdeslam

Author_Institution

Dept. of Comput. Sci., Laval Univ., Montreal, QC, Canada

fYear

2008

fDate

11-13 Dec. 2008

Firstpage

83

Lastpage

90

Abstract

Learning by imitation has shown to be a powerful paradigm for automated learning in autonomous robots. This paper presents a general framework of learning by imitation for stochastic and partially observable systems. The model is a Predictive Policy Representation (PPR) whose goal is to represent the teacher´s policies without any reference to states. The model is fully described in terms of actions and observations only. We show how this model can efficiently learn the personal behavior and preferences of an assistive robot user.

Keywords

collision avoidance; learning systems; mobile robots; predictive control; service robots; stochastic processes; assistive robot user; autonomous robot; imitation learning predictive model; obstacle avoidance; partially observable environment; predictive policy representation; stochastic process; user motion policy; Automatic control; Human robot interaction; Intelligent control; Intelligent robots; Machine learning; Power system modeling; Predictive models; Stochastic systems; Switches; Wheelchairs; Imitation Learning; POMDPs; PSRs;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications, 2008. ICMLA '08. Seventh International Conference on

Conference_Location

San Diego, CA

Print_ISBN

978-0-7695-3495-4

Type

conf

DOI

10.1109/ICMLA.2008.142

Filename

4724959