Header logo is ei

Hierarchical Relative Entropy Policy Search

2012

Conference Paper

ei


Many real-world problems are inherently hierarchically structured. The use of this structure in an agent's policy may well be the key to improved scalability and higher performance. However, such hierarchical structures cannot be exploited by current policy search algorithms. We will concentrate on a basic, but highly relevant hierarchy - the `mixed option' policy. Here, a gating network fi rst decides which of the options to execute and, subsequently, the option-policy determines the action. In this paper, we reformulate learning a hierarchical policy as a latent variable estimation problem and subsequently extend the Relative Entropy Policy Search (REPS) to the latent variable case. We show that our Hierarchical REPS can learn versatile solutions while also showing an increased performance in terms of learning speed and quality of the found policy in comparison to the nonhierarchical approach.

Author(s): Daniel, C. and Neumann, G. and Peters, J.
Book Title: Fifteenth International Conference on Artificial Intelligence and Statistics
Volume: 22
Pages: 273--281
Year: 2012
Month: April
Day: 0

Series: JMLR Proceedings
Editors: Lawrence, N. D. and Girolami, M.
Publisher: JMLR.org

Department(s): Empirical Inference
Research Project(s): Reinforcement Learning
Bibtex Type: Conference Paper (inproceedings)

Event Name: AISTATS 2012
Event Place: La Palma, Canary Islands, Spain

Links: PDF
Web

BibTex

@inproceedings{DanielNP2012,
  title = {Hierarchical Relative Entropy Policy Search},
  author = {Daniel, C. and Neumann, G. and Peters, J.},
  booktitle = {Fifteenth International Conference on Artificial Intelligence and Statistics},
  volume = {22},
  pages = {273--281},
  series = {JMLR Proceedings},
  editors = {Lawrence, N. D. and Girolami, M.},
  publisher = {JMLR.org},
  month = apr,
  year = {2012},
  month_numeric = {4}
}