Knowledge Transfer among Tasks in Reinforcement Learning

• Grant number: 12/02190-9
• Support Opportunities: Scholarships in Brazil - Master
• Start date: July 01, 2012
• End date: May 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Anna Helena Reali Costa
• Grantee: Marcelo Li Koga
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

Transferring the knowledge acquired by a robot in previous experiences to new tasks is one of the challenges faced by the Artificial Intelligence field nowadays. This scientific research project has the objective to propose, develop and evaluate abstraction methods applied to the transfer of policies learned in some tasks by the agent to new, similar and unseen tasks, using the Reinforcement Learning framework. Regarding the abstraction problem, first-order logic will be particularly used as the representation language, in order to achieve generalization of tasks through the power of abstraction of the representation. This knowledge transfer will be explored in various domains, especially the robot navigation domain in places such as buildings and hospitals.

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)

KOGA, MARCELO L.; FREIRE, VALDINEI; COSTA, ANNA H. R.. Stochastic Abstract Policies: Generalizing Knowledge to Improve Reinforcement Learning. IEEE TRANSACTIONS ON CYBERNETICS, v. 45, n. 1, p. 77-88, JAN 2015. (12/02190-9, 11/19280-8)

SILVA, L. O. L. A.; KOGA, M. L.; CUGNASCA, C. E.; COSTA, A. H. R.. Comparative assessment of feature selection and classification techniques for visual inspection of pot plant seedlings. COMPUTERS AND ELECTRONICS IN AGRICULTURE, v. 97, p. 47-55, SEP 2013. (12/02190-9, 11/19280-8)

DA SILVA, VALDINEI FREIRE; KOGA, MARCELO LI; COZMAN, FABIO GAGLIARDI; REALI COSTA, ANNA HELENA; BEHNKE, S; VELOSO, M; VISSER, A; XIONG, R. Reusing Risk-Aware Stochastic Abstract Policies in Robotic Navigation Learning. ROBOCUP 2013: ROBOT WORLD CUP XVII, v. 8371, p. 12-pg., 2014-01-01. (11/19280-8, 12/02190-9)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

KOGA, Marcelo Li. Relational transfer across reinforcement learning tasks via abstract policies.. 2013. Master's Dissertation - Universidade de São Paulo (USP). Escola Politécnica (EP/BC) São Paulo.