The University of Southampton
University of Southampton Institutional Repository

"If you can't be with the one you love, love the one you're with": How individual habituation of agent interactions improves global utility

"If you can't be with the one you love, love the one you're with": How individual habituation of agent interactions improves global utility
"If you can't be with the one you love, love the one you're with": How individual habituation of agent interactions improves global utility
Simple distributed strategies that modify the behaviour of selfish individuals in a manner that enhances cooperation or global efficiency have proved difficult to identify. We consider a network of selfish agents who each optimise their individual utilities by coordinating (or anti?coordinating) with their neighbours, to maximise the pay-offs from randomly weighted pair-wise games. In general, agents will opt for the behaviour that is the best compromise (for them) of the many conflicting constraints created by their neighbours, but the attractors of the system as a whole will not maximise total utility. We then consider agents that act as 'creatures of habit' by increasing their preference to coordinate (anti-coordinate) with whichever neighbours they are coordinated (anti?coordinated) with at the present moment. These preferences change slowly while the system is repeatedly perturbed such that it settles to many different local attractors. We find that under these conditions, with each perturbation there is a progressively higher chance of the system settling to a configuration with high total utility. Eventually, only one attractor remains, and that attractor is very likely to maximise (or almost maximise) global utility. This counterintuitive result can be understood using theory from computational neuroscience; we show that this simple form of habituation is equivalent to Hebbian learning, and the improved optimisation of global utility that is observed results from well?known generalisation capabilities of associative memory acting at the network scale. This causes the system of selfish agents, each acting individually but habitually, to collectively identify configurations that maximise total utility.
hebbian learning, hopfield network, associative memory, game theory, self-­rganisation, adaptive networks
167-181
Davies, Adam
5c959da0-2515-4b94-a7a0-274bbe6d850b
Watson, Richard
ce199dfc-d5d4-4edf-bd7b-f9e224c96c75
Mills, Rob
3d53d4bc-e1de-4807-b89b-f5813f2172a7
Buckley, C.L.
777ec49b-e6e7-4d52-b130-f7b6bcaf3166
Noble, Jason
440f07ba-dbb8-4d66-b969-36cde4e3b764
Davies, Adam
5c959da0-2515-4b94-a7a0-274bbe6d850b
Watson, Richard
ce199dfc-d5d4-4edf-bd7b-f9e224c96c75
Mills, Rob
3d53d4bc-e1de-4807-b89b-f5813f2172a7
Buckley, C.L.
777ec49b-e6e7-4d52-b130-f7b6bcaf3166
Noble, Jason
440f07ba-dbb8-4d66-b969-36cde4e3b764

Davies, Adam, Watson, Richard, Mills, Rob, Buckley, C.L. and Noble, Jason (2011) "If you can't be with the one you love, love the one you're with": How individual habituation of agent interactions improves global utility Artificial Life, 17, (3), Summer Issue, pp. 167-181. (doi:10.1162/artl_a_00030).

Record type: Article

Abstract

Simple distributed strategies that modify the behaviour of selfish individuals in a manner that enhances cooperation or global efficiency have proved difficult to identify. We consider a network of selfish agents who each optimise their individual utilities by coordinating (or anti?coordinating) with their neighbours, to maximise the pay-offs from randomly weighted pair-wise games. In general, agents will opt for the behaviour that is the best compromise (for them) of the many conflicting constraints created by their neighbours, but the attractors of the system as a whole will not maximise total utility. We then consider agents that act as 'creatures of habit' by increasing their preference to coordinate (anti-coordinate) with whichever neighbours they are coordinated (anti?coordinated) with at the present moment. These preferences change slowly while the system is repeatedly perturbed such that it settles to many different local attractors. We find that under these conditions, with each perturbation there is a progressively higher chance of the system settling to a configuration with high total utility. Eventually, only one attractor remains, and that attractor is very likely to maximise (or almost maximise) global utility. This counterintuitive result can be understood using theory from computational neuroscience; we show that this simple form of habituation is equivalent to Hebbian learning, and the improved optimisation of global utility that is observed results from well?known generalisation capabilities of associative memory acting at the network scale. This causes the system of selfish agents, each acting individually but habitually, to collectively identify configurations that maximise total utility.

PDF LTOYW_(PREPRINT).pdf - Other
Download (602kB)

More information

e-pub ahead of print date: 13 July 2011
Published date: August 2011
Keywords: hebbian learning, hopfield network, associative memory, game theory, self-­rganisation, adaptive networks
Organisations: Agents, Interactions & Complexity, EEE

Identifiers

Local EPrints ID: 272431
URI: http://eprints.soton.ac.uk/id/eprint/272431
PURE UUID: e62bb048-66aa-4dfa-a192-6b04d85222a6

Catalogue record

Date deposited: 10 Jun 2011 10:07
Last modified: 18 Jul 2017 06:24

Export record

Altmetrics

Contributors

Author: Adam Davies
Author: Richard Watson
Author: Rob Mills
Author: C.L. Buckley
Author: Jason Noble

University divisions

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

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×