Learning to Coordinate: Co-Evolution and Correlated Equilibrium

Alejandro Lee-Penagos ()
Additional contact information
Alejandro Lee-Penagos: School of Economics, University of Nottingham

No 2016-11, Discussion Papers from The Centre for Decision Research and Experimental Economics, School of Economics, University of Nottingham

Abstract: In a coordination game such as the Battle of the Sexes, agents can condition their plays on external signals that can, in theory, lead to a Correlated Equilibrium that can improve the overall payoffs of the agents. Here we explore whether boundedly rational, adaptive agents can learn to coordinate in such an environment. We find that such agents are able to coordinate, often in complex ways, even without an external signal. Furthermore, when a signal is present, Correlated Equilibrium are rare. Thus, even in a world of simple learning agents, coordination behavior can take on some surprising forms.

Keywords: Battle of the Sexes; Correlated Equilibrium; Evolutionary Game Theory; Learning Algorithms; Coordination Games; Adaptive Agents (search for similar items in EconPapers)
Date: 2016-11
New Economics Papers: this item is included in nep-cbe, nep-cdm, nep-evo, nep-exp, nep-gth, nep-hpe and nep-mic
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nottingham.ac.uk/cedex/documents/paper ... on-paper-2016-11.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:not:notcdx:2016-11

Access Statistics for this paper

More papers in Discussion Papers from The Centre for Decision Research and Experimental Economics, School of Economics, University of Nottingham School of Economics University of Nottingham University Park Nottingham NG7 2RD. Contact information at EDIRC.
Bibliographic data for series maintained by Jose V Guinot Saporta ().