Reference : Policy search in a space of simple closed-form formulas: towards interpretability of ...
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/135635
Policy search in a space of simple closed-form formulas: towards interpretability of reinforcement learning
English
Maes, Francis mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Fonteneau, Raphaël mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Wehenkel, Louis mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Ernst, Damien mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Oct-2012
Discovery Science 15th International Conference, DS 2012, Lyon, France, October 29-31, 2012. Proceedings
Springer
37-51
Yes
No
International
978-3-642-33491-7
Berlin
Germany
The Fifteenth International Conference on Discovery Science (DS 2012)
29-31 October, 2012
[en] Reinforcement Learning ; Formula Discovery ; Interpretability
[en] In this paper, we address the problem of computing interpretable solutions to reinforcement learning (RL) problems. To this end, we propose a search algorithm over a space of simple losed-form formulas that are used to rank actions. We formalize the search for a high-performance policy as a multi-armed bandit problem where each arm corresponds to a candidate policy canonically represented by its shortest formula-based representation. Experiments, conducted on standard benchmarks, show that this approach manages to determine both efficient and interpretable solutions.
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/135635

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Maes2012Ds.pdfPublisher postprint216.26 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
Maes2012DSSlides.pdfThis is a fun comic-book like presentation of this paper !4.76 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.