Data-efficient generalization of robot skills with contextual policy search

Kupcsik, A. G. and Deisenroth, M. P. and Peters, J. and Neumann, Gerhard (2013) Data-efficient generalization of robot skills with contextual policy search. Proceedings of the 27th AAAI Conference on Artificial Intelligence, AAAI 2013 . pp. 1401-1407. ISSN -

Documents
Kupcsik_AAAI_2013.pdf
[img]
[Download]
[img]
Preview
PDF
Kupcsik_AAAI_2013.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

In robotics, controllers make the robot solve a task within a specific context. The context can describe the objectives of
the robot or physical properties of the environment and is always specified before task execution. To generalize the controller to multiple contexts, we follow a hierarchical approach for policy learning: A lower-level policy controls the robot for a given context and an upper-level policy generalizes among contexts. Current approaches for learning such upper-level policies are based on model-free policy search, which require an excessive number of interactions of the robot with its environment.
More data-efficient policy search approaches are model based but, thus far, without the capability of learning
hierarchical policies. We propose a new model-based policy search approach that can also learn contextual upper-level
policies. Our approach is based on learning probabilistic forward models for long-term predictions. Using these redictions, we use information-theoretic insights to improve the upper-level policy. Our method achieves a substantial improvement in learning speed compared to existing methods on simulated and real robotic tasks.

Additional Information:27th AAAI Conference on Artificial Intelligence, AAAI 2013; Bellevue, WA; United States; 14 - 18 July 2013
Keywords:Policy Search, Robotics
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
G Mathematical and Computer Sciences > G760 Machine Learning
H Engineering > H671 Robotics
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25777
Deposited On:03 Feb 2017 11:00

Repository Staff Only: item control page