Title: Transfer learning in reinforcement learning problems through partial policy recycling
Authors: Ramon, Jan ×
Driessens, Kurt
Croonenborghs, Tom #
Issue Date: 2007
Publisher: Springer
Host Document: Lecture Notes in Computer Science vol:4701 pages:699-707
Conference: 18th European Conference on Machine Learning location:Warsaw, Poland date:September 17-21, 2007
Abstract: In this paper we investigate the relation between transfer learning in reinforcement learning with function approximation and supervised learning with concept drift. We present a new incremental relational regression tree algorithm that is capable of dealing with concept drift through tree restructuring and show that it enables a reinforcement learner, more precisely a Q-learner, to transfer knowledge from one task to another by recycling those parts of the generalized Q-function that still hold interesting information for the new task. We illustrate the performance of the algorithm in experiments with both supervised learning tasks with concept drift and reinforcement learning tasks that allow the transfer of knowledge from easier, related tasks.
Description: Acceptance rate = 23%
ISBN: 978-3-540-74957-8
ISSN: 0302-9743
Publication status: published
KU Leuven publication type: IC
Appears in Collections:Informatics Section
Technologiecluster Computerwetenschappen
Computer Science Technology TC, Technology Campus Geel
× corresponding author
# (joint) last author

Files in This Item:
File Status SizeFormat
2007_ecml_ramon.pdf Published 213KbAdobe PDFView/Open


All items in Lirias are protected by copyright, with all rights reserved.

© Web of science