Reference : Active exploration by searching for experiments that falsify the computed control policy
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/88934
Active exploration by searching for experiments that falsify the computed control policy
English
Fonteneau, Raphaël mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Murphy, Susan [ > > ]
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) > Systèmes et modélisation >]
Apr-2011
Proceedings of the 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Yes
International
2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
April 11-15, 2011
Paris
France
[en] reinforcement learning ; active learning ; sequential decision making
[en] We propose a strategy for experiment selection - in the context of reinforcement learning - based on the idea that the most interesting experiments to carry out at some stage are those that are the most liable to falsify the current hypothesis about the optimal control policy. We cast this idea in a context where a policy learning algorithm and a model identification method are given a priori. Experiments are selected if, using the learnt environment model, they are predicted to yield a revision of the learnt control policy. Algorithms and simulation results are provided for a deterministic system with discrete action space. They show that the proposed approach is promising.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
http://hdl.handle.net/2268/88934

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
adprl11_Fonteneau_et_al.pdfPublisher postprint650.08 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.