Reference : Active exploration by searching for experiments that falsify the computed control policy

	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/88934

Title :	Active exploration by searching for experiments that falsify the computed control policy
Language :	English
Author, co-author :	Fonteneau, Raphaël [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Murphy, Susan [ > > ]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Ernst, Damien [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Publication date :	Apr-2011
Main document title :	Proceedings of the 2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Audience :	International
Event name :	2011 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-11)
Event date :	April 11-15, 2011
Event place (city) :	Paris
Event country :	France
Keywords :	[en] reinforcement learning ; active learning ; sequential decision making
Abstract :	[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.
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Permalink :	http://hdl.handle.net/2268/88934

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access adprl11_Fonteneau_et_al.pdf Publisher postprint 650.08 kB View/Open

All documents in ORBi are protected by a user license.

 

© ULg Library Network |  Feedback |  ORBi legal notices

Dspace v1.5