Master’s dissertation (Dissertations and theses)
Learning for exploration/exploitation in reinforcement learning
Castronovo, Michaël
2012
 

Files


Full Text
main.pdf
Author postprint (614.37 kB)
Download
Annexes
main.pdf
Publisher postprint (188.19 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Reinforcement Learning; Exploration/Exploitation dilemma,; Formula discovery
Abstract :
[en] We consider the problem of learning high-performance Exploration/Exploitation (E/E) strategies for finite Markov Decision Processes (MDPs) when the MDP to be controlled is supposed to be drawn from a known probability distribution pM(·). The performance criterion is the sum of discounted rewards collected by the E/E strategy over an infinite length trajectory. We propose an approach for solving this problem that works by considering a rich set of candidate E/E strategies and by looking for the one that gives the best average performances on MDPs drawn according to pM(·). As candidate E/E strategies, we consider index-based strategies parametrized by small formulas combining variables that include the estimated reward function, the number of times each transition has occurred and the optimal value functions ˆ V and ˆQ of the estimated MDP (obtained through value iteration). The search for the best formula is formalized as a multi-armed bandit problem, each arm being associated with a formula. We experimentally compare the performances of the approach with R-max as well as with -Greedy strategies and the results are promising.
Disciplines :
Computer science
Author, co-author :
Castronovo, Michaël ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids
Language :
English
Title :
Learning for exploration/exploitation in reinforcement learning
Defense date :
June 2012
Number of pages :
51
Institution :
ULiège - Université de Liège
Degree :
Master en sciences informatiques, à finalité approfondie
Promotor :
Ernst, Damien  ;  Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Louveaux, Quentin  ;  Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Wehenkel, Louis  ;  Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Geurts, Pierre  ;  Université de Liège - ULiège > Montefiore Institute of Electrical Engineering and Computer Science
Available on ORBi :
since 09 October 2012

Statistics


Number of views
173 (18 by ULiège)
Number of downloads
241 (15 by ULiège)

Bibliography


Similar publications



Sorry the service is unavailable at the moment. Please try again later.
Contact ORBi