Reference : Model-free Monte Carlo-like policy evaluation
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/22651
Model-free Monte Carlo-like policy evaluation
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 >]
May-2010
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)
JMLR W&CP Volume 9
217-224
Yes
No
International
Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)
May 13-15 2010
Chia Laguna, Sardinia
Italy
[en] reinforcement learning ; model free policy evaluation ; Monte Carlo
[en] We propose an algorithm for estimating the finite-horizon expected return of a closed loop control policy from an a priori given (off-policy) sample of one-step transitions. It averages cumulated rewards along a set of “broken trajectories” made of one-step transitions selected from the sample on the basis of the control policy. Under some Lipschitz continuity assumptions on the system dynamics, reward function and control policy, we provide bounds on the bias and variance of the estimator that depend only on the Lipschitz constants, on the number of broken trajectories used in the estimator, and on the sparsity of the sample of one-step transitions.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS ; Fonds pour la formation à la Recherche dans l'Industrie et dans l'Agriculture (Communauté française de Belgique) - FRIA
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/22651
http://jmlr.csail.mit.edu/proceedings/papers/v9/
This paper was also presented at the "Conférence Francophone sur l'Apprentissage Automatique (CAp) 2010" where it won the "Best student paper award".

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Fonteneau2010AISTATS.pdfPublisher postprint1.02 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.