Transfer Learning to Heterogeneous Robotics

• Grant number: 12/14010-5
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: December 01, 2012
• End date: December 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Reinaldo Augusto da Costa Bianchi
• Grantee: Luiz Antonio Celiberto Junior
• Host Institution: Centro Universitário FEI (UNIFEI). Campus de São Bernardo do Campo. São Bernardo do Campo , SP, Brazil

Abstract

This project propose a mechanism for accelerating the reinforcement learning based on transfer learning. This transfer will be happeningwith case based mode that will compose the heuristics that help solving problems more quickly. The research will focus on the main area of multiple heterogeneous agents. The validation results will be made by real robots, which are available in Centro Universitário da FEI and University of Sao Paulo.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BIANCHI, REINALDO A. C.; CELIBERTO, JR., LUIZ A.; SANTOS, PAULO E.; MATSUURA, JACKSON P.; LOPEZ DE MANTARAS, RAMON. Transferring knowledge as heuristics in reinforcement learning: A case-based approach. ARTIFICIAL INTELLIGENCE, v. 226, p. 102-121, SEP 2015. (11/19280-8, 12/04089-3, 12/14010-5)