Header logo is

A Predictive Model for Imitation Learning in Partially Observable Environments

2008

Conference Paper

ei


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.

Author(s): Boularias, A.
Book Title: ICMLA 2008
Journal: Proceedings of the Seventh International Conference on Machine Learning and Applications (ICMLA 2008)
Pages: 83-90
Year: 2008
Month: December
Day: 0
Editors: Wani, M. A., X.-W. Chen, D. Casasent, L. A. Kurgan, T. Hu, K. Hafeez
Publisher: IEEE

Department(s): Empirische Inferenz
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1109/ICMLA.2008.142
Event Name: Seventh International Conference on Machine Learning and Applications
Event Place: San Diego, CA, USA

Address: Piscataway, NJ, USA
Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{6830,
  title = {A Predictive Model for Imitation Learning in Partially Observable Environments},
  author = {Boularias, A.},
  journal = {Proceedings of the Seventh International Conference on Machine Learning and Applications (ICMLA  2008)},
  booktitle = {ICMLA 2008},
  pages = {83-90},
  editors = {Wani, M. A., X.-W. Chen, D. Casasent, L. A. Kurgan, T. Hu, K. Hafeez},
  publisher = {IEEE},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Piscataway, NJ, USA},
  month = dec,
  year = {2008},
  doi = {10.1109/ICMLA.2008.142},
  month_numeric = {12}
}