IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Relational Representations and Traces for Efficient Reinforcement Learning

Relational Representations and Traces for Efficient Reinforcement Learning
View Sample PDF
Author(s): Eduardo F. Morales (National Institute of Astrophysics, Optics and Electronics, México)and Julio H. Zaragoza (National Institute of Astrophysics, Optics and Electronics, México)
Copyright: 2014
Pages: 26
Source title: Robotics: Concepts, Methodologies, Tools, and Applications
Source Author(s)/Editor(s): Information Resources Management Association (USA)
DOI: 10.4018/978-1-4666-4607-0.ch013

Purchase

View Relational Representations and Traces for Efficient Reinforcement Learning on the publisher's website for pricing and purchasing information.

Abstract

This chapter introduces an approach for reinforcement learning based on a relational representation that: (i) can be applied over large search spaces, (ii) can incorporate domain knowledge, and (iii) can use previously learned policies on different, but similar, problems. The underlying idea is to represent states as sets of first order relations, actions in terms of those relations, and to learn policies over such generalized representation. It is shown how this representation can produce powerful abstractions and that policies learned over this generalized representation can be directly applied, without any further learning, to other problems that can be characterized by the same set of relations. To accelerate the learning process, we present an extension where traces of the tasks to be learned are provided by the user. These traces are used to select only a small subset of possible actions increasing the convergence of the learning algorithms. The effectiveness of the approach is tested on a flight simulator and on a mobile robot.

Related Content

Rashmi Rani Samantaray, Zahira Tabassum, Abdul Azeez. © 2024. 32 pages.
Sanjana Prasad, Deepashree Rajendra Prasad. © 2024. 25 pages.
Deepak Varadam, Sahana P. Shankar, Aryan Bharadwaj, Tanvi Saxena, Sarthak Agrawal, Shraddha Dayananda. © 2024. 24 pages.
Tarun Kumar Vashishth, Vikas Sharma, Kewal Krishan Sharma, Bhupendra Kumar, Sachin Chaudhary, Rajneesh Panwar. © 2024. 29 pages.
Mrutyunjaya S. Hiremath, Rajashekhar C. Biradar. © 2024. 30 pages.
C. L. Chayalakshmi, Mahabaleshwar S. Kakkasageri, Rajani S. Pujar, Nayana Hegde. © 2024. 30 pages.
Amit Kumar Tyagi. © 2024. 29 pages.
Body Bottom