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

Haitham Bou Ammar, Decebal Constantin Mocanu, Matthew E. Taylor, Kurt Driessens, Karl Tuyls, Gerhard Weiss

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

16 Citations (Scopus)
1 Downloads (Pure)


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
Subtitle of host publicationEuropean Conference, ECML PKDD 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings
EditorsHendrik Blockeel, Kristian Kersting, Siegfried Nijssen, Filip Železný
Place of PublicationBerlin, Heidelberg
Number of pages16
VolumePart II
ISBN (Electronic)978-3-642-40991-2
ISBN (Print)978-3-642-40990-5
Publication statusPublished - 2013
Externally publishedYes

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence


  • Boltzmann machines
  • Inter-task mapping
  • Least squares policy iteration
  • Reinforcement learning
  • Transfer learning

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