Learning strict Nash equilibria through reinforcement
Learning strict Nash equilibria through reinforcement
This paper studies the analytical properties of the reinforcement learning model proposed in Erev and Roth (1998), also termed cumulative reinforcement learning in Laslier et al. (2001).
The main results of the paper show that, if the solution trajectories of the underlying replicator equation converge exponentially fast, then, with probability arbitrarily close to one, all the pathwise realizations of the reinforcement learning process will, from some time on, lie within an ?? band of that solution. The paper improves upon results currently available in the literature by showing that a reinforcement learning process that has been running for some time and is found sufficiently close to a strict Nash equilibrium, will reach it with probability one
learning, law of effect, power law of practice, strict nash equilibrium, replicator dynamics
148-155
Ianni, Antonella
35024f65-34cd-4e20-9b2a-554600d739f3
January 2014
Ianni, Antonella
35024f65-34cd-4e20-9b2a-554600d739f3
Abstract
This paper studies the analytical properties of the reinforcement learning model proposed in Erev and Roth (1998), also termed cumulative reinforcement learning in Laslier et al. (2001).
The main results of the paper show that, if the solution trajectories of the underlying replicator equation converge exponentially fast, then, with probability arbitrarily close to one, all the pathwise realizations of the reinforcement learning process will, from some time on, lie within an ?? band of that solution. The paper improves upon results currently available in the literature by showing that a reinforcement learning process that has been running for some time and is found sufficiently close to a strict Nash equilibrium, will reach it with probability one
Text
article/pii/S0304406813000323
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 10 April 2013
e-pub ahead of print date: 19 April 2013
Published date: January 2014
Keywords:
learning, law of effect, power law of practice, strict nash equilibrium, replicator dynamics
Organisations:
Economics
Identifiers
Local EPrints ID: 354242
URI: http://eprints.soton.ac.uk/id/eprint/354242
ISSN: 0304-4068
PURE UUID: 1754acba-117d-45c5-8706-226b8fce4e13
Catalogue record
Date deposited: 05 Jul 2013 13:31
Last modified: 15 Mar 2024 02:51
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
