Automatically mapped transfer between reinforcement learning tasks via three-way restricted Boltzmann machines

H. Bou Ammar, D.C. Mocanu, M.E. Taylor, K. Driessens, K.P. Tuyls, G. Weiss

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

16 Citations (Scopus)
79 Downloads (Pure)

Abstract

Existing reinforcement learning approaches are often hampered by learning tabula rasa. Transfer for reinforcement learning tackles this problem by enabling the reuse of previously learned results, but may require an inter-task mapping to encode how the previously learned task and the new task are related. This paper presents an autonomous framework for learning inter-task mappings based on an adaptation of restricted Boltzmann machines. Both a full model and a computationally efficient factored model are introduced and shown to be effective in multiple transfer learning scenarios.
Original languageEnglish
Title of host publicationMachine Learning and Knowledge Discovery in Databases : European Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part II
EditorsH. Blockeel, K. Kersting, S. Nijssen, F. Zelezny
Place of PublicationBerlin
PublisherSpringer
Pages449-464
ISBN (Print)978-3-642-40990-5
DOIs
Publication statusPublished - 2013
EventEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, September 23-27, 2013, Prague, Czech Republic - Prague, Czech Republic
Duration: 23 Sep 201327 Sep 2013
http://www.ecmlpkdd2013.org/

Publication series

NameLecture Notes in Computer Science
Volume8189
ISSN (Print)0302-9743

Conference

ConferenceEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, September 23-27, 2013, Prague, Czech Republic
Abbreviated titleECMLPKDD 2013
CountryCzech Republic
CityPrague
Period23/09/1327/09/13
Internet address

Fingerprint Dive into the research topics of 'Automatically mapped transfer between reinforcement learning tasks via three-way restricted Boltzmann machines'. Together they form a unique fingerprint.

Cite this