@inproceedings{346a341218d64ce49c20f28a3e4e942a,
title = "Automatically mapped transfer between reinforcement learning tasks via three-way restricted Boltzmann Machines",
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.",
keywords = "Boltzmann machines, Inter-task mapping, Least squares policy iteration, Reinforcement learning, Transfer learning",
author = "Ammar, {Haitham Bou} and Mocanu, {Decebal Constantin} and Taylor, {Matthew E.} and Kurt Driessens and Karl Tuyls and Gerhard Weiss",
year = "2013",
doi = "10.1007/978-3-642-40991-2_29",
language = "English",
isbn = "978-3-642-40990-5",
volume = "Part II",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "449--464",
editor = "Hendrik Blockeel and Kristian Kersting and Siegfried Nijssen and Filip {\v Z}elezn{\'y}",
booktitle = "Machine Learning and Knowledge Discovery in Databases",
}