A Simple Computational Theory of General Collective Intelligence

Topics in Cognitive Science 11 (2):374-392 (2019)
  Copy   BIBTEX

Abstract

What are the conditions under which groups of agents will perform well across multiple tasks? The author establishes a set of “alignment conditions” that enforce identity of beliefs and desires across agents. These conditions are necessary and sufficient for ensuring that a multiagent system behaves as if controlled by a rational centralized controller. Several widely observed social phenomena can be understood as facilitating the alignment conditions.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 91,219

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Knowledge-based clustering in computational intelligence.Witold Pedrycz - 2007 - In Wlodzislaw Duch & Jacek Mandziuk (eds.), Challenges for Computational Intelligence. Springer. pp. 317--341.
Computational Intelligence in Mind Games.Jacek Mańdziuk - 2007 - In Wlodzislaw Duch & Jacek Mandziuk (eds.), Challenges for Computational Intelligence. Springer. pp. 407--442.
Mandevillian Intelligence.Paul R. Smart - 2018 - Synthese 195 (9):4169-4200.

Analytics

Added to PP
2018-06-14

Downloads
19 (#753,814)

6 months
2 (#1,157,335)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

Add more citations

References found in this work

Cognition in the Wild.Edward Hutchins - 1995 - Critica 27 (81):101-105.
Team Reasoning and Intentional Cooperation for Mutual Benefit.Robert Sugden - 2014 - Journal of Social Ontology 1 (1):143–166.
Collaborative plans for complex group action.Barbara J. Grosz & Sarit Kraus - 1996 - Artificial Intelligence 86 (2):269-357.
The experimental study of social preferences.Matthew Rabin - 2006 - Social Research: An International Quarterly 73 (2):405-428.

Add more references