Reference : Statistical mechanics approach to a reinforcement learning model with memory
Scientific journals : Article
Engineering, computing & technology : Computer science
Physical, chemical, mathematical & earth Sciences : Physics
Statistical mechanics approach to a reinforcement learning model with memory
Lipowski, A. [> > > >]
Gontarek, K. [> > > >]
Ausloos, Marcel mailto [Université de Liège - ULiège > Département de physique > Département de physique > >]
Physica A: Statistical Mechanics and its Applications
Elsevier Science
Yes (verified by ORBi)
The Netherlands
[en] We introduce a two-player model of reinforcement learning with memory. Past actions of an iterated game are stored in a memory and used to determine player's next action. To examine the behaviour of the model some approximate methods are used and confronted against numerical simulations and exact master equation. When the length of memory of players increases to infinity the model undergoes ail absorbing-state phase transition. Performance of examined strategies is checked in the prisonor' dilemma game. It turns out that it is advantageous to have a large memory in symmetric games, but it is better to have a short memory in asymmetric ones. (C) 2009 Elsevier B.V. All rights reserved.
Researchers ; Professionals

File(s) associated to this reference

Fulltext file(s):

Restricted access
Statistical mechanics approach Ausloos 2009.pdfPublisher postprint722.68 kBRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.