The Evolution of Conventions
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
The author shows how a group of individuals can learn to play a coordination game without any common knowledge and with only a small amount of rationality. The game is repeated many times by different players. Each player chooses an optimal reply based on incomplete information about what other players have done in the past. Occasionally they make mistakes. When the likelihood of mistakes is very small, typically one coordination equilibrium will be played almost all of the time over the long run. This stochastically stable equilibrium can be computed analytically using a general theorem the author proves on perturbed Markov processes. Copyright 1993 by The Econometric Society.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Theoretical extensions of this approach have argued that purely local interactions taking place on social networks can lead to population-wide, or “global,” coordinated behavior (1, 2, 6, 45).”
From Emergent social conventions and collective bias in LLM populations (2025) · cites this paper as [1]
Citations
Cites
Schelling, T. C. (1960) · Cited by 11,815
Convention: A Philosophical Study.
Llewelyn, J. E., & Lewis, D. K. (1970) · The Philosophical Quarterly · doi:10.2307/2218418 · Cited by 3,121
Random perturbations of dynamical systems
(1997) · Translations of Mathematical Monographs · doi:10.1090/mmono/161/03 · Cited by 2,584
A General Theory of Equilibrium Selection in GamesPreprint
Harsanyi, J. C., & Selten, R. (1988) · RePEc: Research Papers in Economics · Cited by 2,104
Learning, Mutation, and Long Run Equilibria in Games
Kandori, M., Mailath, G. J., & Rob, R. (1993) · Econometrica · doi:10.2307/2951777 · Cited by 2,044
Evolutionary Games in Economics
Friedman, D. (1991) · Econometrica · doi:10.2307/2938222 · Cited by 1,939
Ants, Rationality, and Recruitment
Kirman, A. (1993) · The Quarterly Journal of Economics · doi:10.2307/2118498 · Cited by 983
Stochastic evolutionary game dynamics∗
Foster, D., & Young, P. (1990) · Theoretical Population Biology · doi:10.1016/0040-5809(90)90011-j · Cited by 948
An Evolutionary Model of Bargaining
Young, H. P. (1993) · Journal of Economic Theory · doi:10.1006/jeth.1993.1009 · Cited by 374
Self-citationEvolution and Cooperation in Noisy Repeated GamesPreprint
Fudenberg, D., & Maskin, E. S. (1990) · American Economic Review · Cited by 368
Cited by
Items 801–900 of 1,001
Forno, A. D., & Merlone, U. (2002) · Institutional Research Information System University of Turin (University of Turin) · Cited by 16
Cascini, G. (2004) · Proceedings e report · doi:10.36253/88-8453-220-5 · Cited by 16
Fast convergence in evolutionary models: A Lyapunov approach
Ellison, G., Fudenberg, D., & Imhof, L. A. (2015) · Journal of Economic Theory · doi:10.1016/j.jet.2015.10.008 · Cited by 16
Learning efficient correlated equilibria
Borowski, H., Marden, J. R., & Shamma, J. S. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7040463 · Cited by 16
“The theory of resistance trees presented in [25] provides efficient mechanisms for computing the support of the limiting stationary distribution, i.”
BackgroundMethodInfluentialLocation choice by households and polluting firms: An evolutionary approach
Dijkstra, B. R., & de Vries, F. P. (2004) · European Economic Review · doi:10.1016/j.euroecorev.2004.09.006 · Cited by 16
Portfolio manager behavior and global financial crises
Feldman, T. J. (2010) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2010.03.014 · Cited by 16
A Theoretical Examination of Practical Game Playing: Lookahead Search
Mirrokni, V., Thain, N., & Vetta, A. R. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33996-7_22 · Cited by 16
“As well as best-response dynamics, noisy best-response dynamics [21] [80] [52], where players occasionally make mistakes, simultaneous Nash dynamics [7], where all players change their strategies simultaneously, second-order Nash equilibria [8], where beginning with Nash equilibria the set of…”
BackgroundReference-dependent preferences, super-dominance and stochastic stability
Sawa, R., & Wu, J. (2018) · Journal of Mathematical Economics · doi:10.1016/j.jmateco.2018.08.002 · Cited by 13
“…the risk-dominant equilibrium in 2×2 coordination games if individuals adopt the best response with mutations rule (BRM) (Kandori et al. 1993 and Young 1993), i.e. the best response choice rule (Cournot, 1838) plus uniform errors, or the logit choice rule (Blume 1993).2 Since then, a variety…”
BackgroundMethodDecentralized trade, random utility and the evolution of social welfare
Kandori, M., Serrano, R., & Volij, O. (2008) · Journal of Economic Theory · doi:10.1016/j.jet.2007.02.002 · Cited by 16
“Young (1993b) obtains asymmetric Nash solutions as the limits of an evolutionary process in which pairs of agents play the Nash demand game.”
BackgroundResultGoyal, S. (2011) · Handbook of social economics · doi:10.1016/b978-0-444-53187-2.00015-2 · Cited by 24
Multi-level evolution in population games
Canals, J. X. E., & Vega‐Redondo, F. (1998) · International Journal of Game Theory · doi:10.1007/bf01243192 · Cited by 16
Jalons pour une analyse conventionnaliste de la responsabilité sociale de l'entreprise
Postel, N., & Rousseau, S. (2010) · Revue de l’organisation responsable · doi:10.3917/ror.051.0039 · Cited by 19
The strategic advantage of interdependent preferences in rent-seeking contests
Guse, T., & Hehenkamp, B. (2006) · Public Choice · doi:10.1007/s11127-006-9033-0 · Cited by 16
Stochastic evolution with slow learning
Beggs, A. W. (2002) · Economic Theory · doi:10.1007/pl00004218 · Cited by 16
“There has been substantial interest in evolutionary models of equilibrium selection since the work of Kandori, Mailath and Rob (1993) and Young (1993).”
InfluentialA Modified Q-Learning Algorithm for Potential Games
Wang, Y., & Pavel, L. (2014) · IFAC Proceedings Volumes · doi:10.3182/20140824-6-za-1003.02646 · Cited by 16
“Guaranteed convergence to a Nash equilibrium in potential games has been shown for adaptive play and the broad class of finite-memory better-reply processes Young (1993), Young (2005).”
BackgroundInfluentialAdaptive learning, evolutionary dynamics and equilibrium selection in games
Marimon, R. (1993) · European Economic Review · doi:10.1016/0014-2921(93)90050-k · Cited by 16
Sally, D. (2002) · Rationality and Society · doi:10.1177/1043463102014001004 · Cited by 18
Emergent Conventions in Evolutionary GamesPreprint
Huyck, J. B. V. (2008) · RePEc: Research Papers in Economics · Cited by 16
Self-organizing Innovation Networks: When do Small Worlds Emerge?Preprint
Φ, N. C., & Roux, P. (2005) · European Journal of Economic and Social Systems · Cited by 19
Metamimetic Games : Modeling Metadynamics in Social CognitionPreprint
Chavalarias, D. (2005) · arXiv (Cornell University) · doi:10.48550/arxiv.nlin/0508006 · Cited by 16
Hahn, F. (1996) · Economics and Philosophy · doi:10.1017/s0266267100004156 · Cited by 16
Social Approval, Values, and AFDC: A Re-Examination of the Illegitimacy Debate
Nechyba, T. J. (1999) · National Bureau of Economic Research · doi:10.3386/w7240 · Cited by 16
Measuring Peer Effects on Youth Smoking BehaviorPreprint
Nakajima, R. (2004) · SSRN Electronic Journal · doi:10.2139/ssrn.537544 · Cited by 16
Vanderschraaf, P. (2023) · Cambridge University Press eBooks · doi:10.1017/9781108588638 · Cited by 18
Wu, J., Chen, Q., Jiang, H., Wang, H., Xie, Y., Xu, W., Zhou, P., Xu, Z., Chen, L., Li, B., et al. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3385797 · Cited by 15
“According to Lemma 1 in [51], we learn that the stochastically stable strategy profiles are strategy profiles with minimum stochastic potential, and a strategy profile is a stochastically stable strategy profile only if it is in a recurrent class of unperturbed process P .”
BackgroundDynamics of the Bush-Mosteller Learning Algorithm in 2x2 Games
Luis, R., & Segismundo, S. (2008) · doi:10.5772/5282 · Cited by 15
“These are called stochastically stable equilibria (Foster & Young, 1990; Young, 1993; Ellison, 2000).”
Coordination in evolving networks with endogenous decay
Feri, F., & Meléndez-Jímenez, M. A. (2013) · Journal of Evolutionary Economics · doi:10.1007/s00191-013-0313-9 · Cited by 15
“For instance, Kandori et al. (1993) and Young (1993), among others, focus on dynamic models with (bounded rational) agents from a single homogeneous society who interact over time, and are occasionally subjected to mutations.”
Dynamics and stability of potential hyper-networked evolutionary games
Liu, T., Wang, Y., & Cheng, D. (2017) · Machine Intelligence Research · doi:10.1007/s11633-017-1056-0 · Cited by 15
“In this paper we consider mainly only one, which is called the Myopic Best Response Adjustment Rule (MBRAR) [30].”
MethodDecentralized Heterogeneous Multi-Player Multi-Armed Bandits With Non-Zero Rewards on Collisions
Magesh, A., & Veeravalli, V. V. (2021) · IEEE Transactions on Information Theory · doi:10.1109/tit.2021.3136095 · Cited by 24
“The process P is a regular perturbed Markov process if for any z, z′ ∈ Z (Equations (6),(7) and (8) of Appendix of [27]):”
BackgroundMethodCache policies for linear utility maximization
Neglia, G., Carra, D., & Michiardi, P. (2017) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2017.8057192 · Cited by 16
“Our analysis follows the regular perturbation approach made popular by Young to study the stochastically stable equilibria in games with trembling hands [18].”
InfluentialLearning in Potential Games for Electric Power Grids: Models, Dynamics, and Outlook
Wang, S., Du, L., & Marden, J. R. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3176535 · Cited by 15
Stability under Strategy Switching
Paul, S., Ramanujam, R., & Simon, S. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-03073-4_40 · Cited by 16
“Dynamic learning has been extensively studied in game theory: for instance, Young ([15],[16]) considers a model in which each player chooses an optimal strategy based on a sample of information about what other players have done in the past.”
BackgroundA Classification of Weakly Acyclic Games
Apt, K. R., & Simon, S. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33996-7_1 · Cited by 15
Imitation and evolutionary stability of poverty traps
Carrera, E. J. S. (2011) · Journal of Bioeconomics · doi:10.1007/s10818-011-9114-0 · Cited by 22
“One branch of this literature (for example Young 1993, 2001; Kandori et al. 1993; Binmore and Samuelson 1997) investigates stable patterns of behavior as limit points of various adaptive dynamics.”
BackgroundModeling uncertainty in leading ad hoc teams
Agmon, N., Barrett, S., & Stone, P. (2014) · Adaptive Agents and Multi-Agents Systems · doi:10.5555/2615731.2615797 · Cited by 15
Communication networks in markets
Gallo, E. (2020) · European Economic Review · doi:10.1016/j.euroecorev.2020.103545 · Cited by 16
Decentralized Pricing and the equivalence between Nash and Walrasian equilibrium
Mandel, A., & Gintis, H. M. (2016) · Journal of Mathematical Economics · doi:10.1016/j.jmateco.2015.12.008 · Cited by 15
The Impact of Complex and Informed Adversarial Behavior in Graphical Coordination Games
Paarporn, K., Canty, B., Brown, P. N., Alizadeh, M., & Marden, J. R. (2020) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2020.3038842 · Cited by 15
“More detailed treatments can be found in [21], [37].”
BackgroundInfluentialTransitions between equilibria in bilingual games under logit choice
Arigapudi, S. (2019) · Journal of Mathematical Economics · doi:10.1016/j.jmateco.2019.10.004 · Cited by 15
On the dynamics of word of mouth learningwith and without anticipations
Dawid, H. (1999) · Annals of Operations Research · doi:10.1023/a:1018983808923 · Cited by 15
“Among the most extensively studied approaches are fictitious play [5,16] and stochastic best response dynamics [4,9,13,14,21,26].”
BackgroundOn the level of cooperative behavior in a local-interaction model
Tieman, A. F., Houba, H. E. D., & van der Laan, G. (2000) · Journal of Economics · doi:10.1007/bf01227494 · Cited by 15
In-class Simulations of the Iterated Prisoner's Dilemma Game
Bodo, P. (2002) · The Journal of Economic Education · doi:10.1080/00220480209595187 · Cited by 17
“Repeated prisoner's dilemma games are applied to explain how essential social and economic institutions emerge endogenously (Sugden 1989; Elster 1989; Young 1993) and how agents learn (Ellison 1993; Fudenberg and Levine 1998).”
BackgroundConvergence guarantees for a decentralized algorithm achieving pareto optimality
Menon, A., & Baras, J. S. (2013) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2013.6580118 · Cited by 15
“Lemma 3.1 (see [9], Lemma 1): The stationary distribution µ(ε) of P(ε) satisfies lim ε→0 µ(ε) = µ(0), where µ(0) is a stationary distribution of the unperturbed chain P(0).”
BackgroundInfluentialLearning Near-Pareto-Optimal Conventions in Polynomial Time
Wang, X., & Sandholm, T. (2003) · Cited by 15
Social Networks and the Dynamics of Labor Market Outcomes: Evidence from Refugees ¤
Beaman, L. A. (2008) · Cited by 17
On the principle of coordination
Janssen, M. C. W. (2001) · Economics and Philosophy · doi:10.1017/s0266267101000244 · Cited by 15
“Kandori, Mailath and Rob (1993) and Young (1993), among others, study a population of agents interacting in an evolutionary environment and show that the risk dominant equilibrium is selected in the long run.”
BackgroundStochastic better-reply dynamics in finite games
Josephson, J. (2007) · Economic Theory · doi:10.1007/s00199-007-0230-y · Cited by 15
“…s and m of Theorem 1 can at least be weakened to s (L + 2) ≤ m, where L = maxx L(x), and L(x) is the length of the shortest sequence of better replies from x to a strict Nash equilibrium (see Theorem 1 in Young 1993). quasi-concave two-player games, and (v) Almost all transversal aggregative games.”
BackgroundMethodResultInfluentialStochastic stability in a double auction
Agastya, M. K. (2004) · Games and Economic Behavior · doi:10.1016/j.geb.2003.09.010 · Cited by 15
Botman, D. P. J., & Jager, H. (2002) · Journal of International Economics · doi:10.1016/s0022-1996(01)00166-0 · Cited by 15
Distributed coverage games for mobile visual sensor networksPreprint
Zhu, M., & Martı́nez, S. (2010) · arXiv (Cornell University) · doi:10.48550/arxiv.1002.0367 · Cited by 15
“ℓ-trees on G. The resistance of an ℓ-tree is the sum of the resistances of its edges. The stochastic potential of the recurrent class Hℓ is the least resistance among all ℓ-trees in G(ℓ). Theorem6.6([31]). Let {Pǫ t} be a regular perturbation of {P0 t }, and for each ǫ > 19 0, let µ(ǫ) be the unique stationary dist…”
BackgroundMethodInfluentialBEHAVIORAL FOUNDATIONS AND EQUILIBRIUM NOTIONS FOR SOCIAL NETWORK FORMATION PROCESSES
Φ, N. C., & Roux, P. (2004) · Advances in Complex Systems · doi:10.1142/s021952590400007x · Cited by 14
Challenging Conformity: A Case for DiversityPreprint
Kets, W. (2016) · SSRN Electronic Journal · doi:10.2139/ssrn.2871490 · Cited by 16
“Some models in the literature on learning and evolution predict that a particular Nash equilibrium (such as the risk-dominant Nash equilibrium) is selected in the limit (e.g., Kandori et al., 1993; Young, 1993).”
Convention and the Origins of Ownership
Smead, R., & Forber, P. (2020) · Philosophy of Science · doi:10.1086/710626 · Cited by 14
Adaptive play stabilizes cooperation in continuous public goods games
Wu, T., & Wang, L. (2017) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2017.12.102 · Cited by 14
Relative Best Response Dynamics in finite and convex Network Games
Govaert, A., Cenedese, C., Grammatico, S., & Cao, M. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029821 · Cited by 14
“These extended research efforts have resulted in the identification of several classes of games that converge to a pure Nash equilibrium under a variety of such best response processes [7]–[10] and brought forth a number of algorithms that ensure convergence to an equilibrium [11]–[13].”
BackgroundWeakly-Acyclic (Internet) Routing Games
Engelberg, R., & Schapira, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24829-0_26 · Cited by 14
Agent-based dynamics in the general equilibrium model
Mandel, A. (2012) · Complexity Economics · doi:10.7564/12-coec6 · Cited by 15
“This has been showed for exchange economies in two recent contributions of Gintis (2006, 2007) where strong properties of convergence to equilibrium are obtained in a framework where agents use private prices as conventions in the sense of Peyton-Young (1993).”
BackgroundCooperation and cultural transmission in a coordination game
Calabuig, V., & Olcina, G. (2009) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2009.05.005 · Cited by 14
“However, in section 3 we have shown that for initial preference distributions greater than p′, there are two possible equilibria in the society depending on whether the population coordinates in the cooperative equilibrium or in the non-cooperative equilibrium. Therefore, for these values of the parameters we still ha…”
On acyclicity of games with cycles
Andersson, D., Gurvich, V., & Hansen, T. D. (2010) · Discrete Applied Mathematics · doi:10.1016/j.dam.2010.02.006 · Cited by 14
Real-time tacit bargaining, payoff focality, and coordination complexity: Experimental evidence
Luhan, W. J., Poulsen, A., & Roos, M. W. M. (2017) · Games and Economic Behavior · doi:10.1016/j.geb.2017.02.016 · Cited by 14
“…and historical precedent (see for example Van Huyck et al., 1990 and Huyck et al., 1992; Anbarci and Feltovich, 2013, 2016; Gächter and Riedl, 2005; Galeotti et al., 2016; Isoni et al., 2013, 2014; Janssen, 2006; Roth and Murnighan, 1982; Schelling, 1960; Sugden, 1986, and Young, 1993).”
BackgroundSelecting efficient correlated equilibria through distributed learning
Marden, J. R. (2017) · Games and Economic Behavior · doi:10.1016/j.geb.2017.09.007 · Cited by 13
“We prove this theorem using the theory of resistance tree for regular perturbed processes developed in [20].”
MethodInequality and inequity in the emergence of conventions
Cochran, C. T., & O’Connor, C. (2019) · Politics Philosophy & Economics · doi:10.1177/1470594x19828371 · Cited by 14
“There is a long tradition of using mini versions of the bargaining game in evolutionary models (Young, 1993b; Skyrms, 1994).”
BackgroundMethodA prospect theory Nash bargaining solution and its stochastic stability
Sawa, R. (2020) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2020.11.009 · Cited by 13
Exploring the Strategy Space of Negotiating Agents
Baarslag, T. (2016) · Springer theses · doi:10.1007/978-3-319-28243-5 · Cited by 14
A note on control costs and logit rules for strategic games
Baron, R., Durieu, J., Haller, H., & Solal, P. (2002) · Journal of Evolutionary Economics · doi:10.1007/s00191-002-0135-7 · Cited by 14
“In some of the literature, notably Blume (1993, 1995, 1997), Young (1993, 1998) , Kandori, Mailath and Rob (1993), Ellison (1993, 2000), Rhode and Stegeman (1996), Haller and Outkin (1999), and Baron et al. (2002), the agents choose a best reply to their static expectations.”
BackgroundCooperation, Mimesis, and Local Interaction
Eshel, I., Herreiner, D. K., Samuelson, L., Sansone, E., & Shaked, A. (2000) · Sociological Methods & Research · doi:10.1177/0049124100028003006 · Cited by 14
Exploiting focal points among alternative solutions: Two approaches
Kraus, S., Rosenschein, J. S., & Fenster, M. (2000) · Annals of Mathematics and Artificial Intelligence · doi:10.1023/a:1018908306970 · Cited by 14
Dressing the mind properly for the game
Sally, D. (2003) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2002.1246 · Cited by 17
“In a simulated ecology of matrix games, reproductive success accrued to players who favoured the risk-dominant action (Kandori et al. 1993; Young 1993).”
BackgroundLearning of equilibria by a population with minimal information
Dawid, H. (1997) · Journal of Economic Behavior & Organization · doi:10.1016/s0167-2681(96)00016-9 · Cited by 14
Stochastic Darwinian equilibria in small and large populations
Stegeman, M., & Rhode, P. W. (2004) · Games and Economic Behavior · doi:10.1016/j.geb.2003.10.005 · Cited by 14
Incentives in Organizations: An Overview of Some of the Evidence and Theory
MacLeod, W. B. (2001) · Cited by 14
Holdup and the evolution of bargaining conventions
Dawid, H., & MacLeod, W. B. (2001) · European Journal of Economic and Social Systems · doi:10.1051/ejess:2001102 · Cited by 14
Social Networks in Determining Employment and Wages: Patterns, Dynamics, and Inequality
Calvó‐Armengol, A., & Jackson, M. O. (2002) · CaltechAUTHORS (California Institute of Technology) · doi:10.7907/b2v43-0c139 · Cited by 14
A strategic model of complex networks formationPreprint
Φ, N. C., & Roux, P. (2006) · RePEc: Research Papers in Economics · Cited by 14
Complementarity and Social NetworksPreprint
Bramoullé, Y. (2007) · SSRN Electronic Journal · doi:10.2139/ssrn.1028335 · Cited by 14
“In most settings, when everybody interacts with everybody, all agents eventually coordinate on the risk-dominant strategy, e.g., Young (1993), Kandori et al. (1993), Blume (1999).”
BackgroundMethodSubmodularity and the Evolution of Walrasian BehaviorPreprint
Schipper, B. C. (2004) · SSRN Electronic Journal · doi:10.2139/ssrn.369360 · Cited by 14
Evolution of Social NetworksPreprint
Hellmann, T., & Staudigl, M. (2012) · SSRN Electronic Journal · doi:10.2139/ssrn.2321900 · Cited by 15
Binmore, K., & Samuelson, L. (1994) · European Economic Review · doi:10.1016/0014-2921(94)90122-8 · Cited by 14
Coordinated Selfish Distributed Caching for Peering Content-Centric Networks
Pacifici, V., & Dán, G. (2016) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2016.2541320 · Cited by 15
“Lemma 1 (Young [19]): Let P ε be a regular perturbed Markov process, and let μ ε be the unique stationary distribution of P ε for each ε > 0 .”
BackgroundResultInfluentialPolarization on Social Media: Micro-Level Evidence and Macro-Level Implications
Keijzer, M. A., Mäs, M., & Flache, A. (2024) · Journal of Artificial Societies and Social Simulation · doi:10.18564/jasss.5298 · Cited by 24
Variable preference relations: Existence of maximal elements
Luc, D. T., & Soubeyran, A. (2013) · Journal of Mathematical Economics · doi:10.1016/j.jmateco.2013.05.004 · Cited by 12
“…Koszegi and Rabin 2006 [16]), Nash equilibrium, generalized Nash equilibrium, evolutionary stable equilibrium (Thomas 1985 [26]), norms, conventions (Young 1993 [29]), innovation frontier, Pareto solutions, bargaining solutions, focal points (Schelling 1960 [21]), ideal points, cycling points…”
BackgroundLearning to Play Efficient Coarse Correlated Equilibria
Borowski, H., Marden, J. R., & Shamma, J. S. (2018) · Dynamic Games and Applications · doi:10.1007/s13235-018-0244-z · Cited by 13
“Theorem 3 ([34]) Let P 0 be the transition matrix for a stationary Markov process over the finite state space X with recurrent communication classes Y 1 , . . . , Y m .”
BackgroundMethodInfluentialHe, J., Luo, X., Zhang, Z.-L., & Yang, Y. L. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18168595 · Cited by 17
“Moreover, they may even make wrong decisions and the strategies they made may affect each other [27].”
BackgroundA distributed learning algorithm with bit-valued communications for multi-agent welfare optimization
Menon, A., & Baras, J. S. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760240 · Cited by 13
“The general theory is reviewed in Section III and two important results are stated - Theorem 2 from [14] and Theorem 3 from [2].”
BackgroundSkyrms, B. (2003) · Cambridge University Press eBooks · doi:10.1017/cbo9781139165228.007 · Cited by 13
On Synchronous Binary Log-Linear Learning and Second Order Q-learning
Hasanbeig, M., & Pavel, L. (2017) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2017.08.1326 · Cited by 13
Personal research, second opinions, and the diagnostic effort of experts
Agarwal, R., Liu, C., & Prasad, K. (2018) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2018.11.012 · Cited by 19
Conflict leads to cooperation in demand bargaining
Rozen, K. (2012) · Journal of Economic Behavior & Organization · doi:10.1016/j.jebo.2012.12.005 · Cited by 13
Positive feedback in coordination games: Stochastic evolutionary dynamics and the logit choice rule
Hwang, S., & Rey-Bellet, L. (2021) · Games and Economic Behavior · doi:10.1016/j.geb.2021.01.003 · Cited by 15
Generalized efficiency bounds in distributed resource allocation
Marden, J. R., & Roughgarden, T. (2010) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2010.5717472 · Cited by 13
HIV/AIDS and Fatalism: Should Prevention Campaigns Disclose the Transmission Rate of HIV?
Sterck, O. C. (2013) · Journal of African Economies · doi:10.1093/jae/ejt018 · Cited by 17
Anti-Malthus: Conflict and the evolution of societies
Levine, D. K., & Modica, S. (2013) · Research in Economics · doi:10.1016/j.rie.2013.09.004 · Cited by 15
“We use the characterization of stochastically stable states given by Young [63].”
BackgroundMethodInfluentialEquilibrium Selection Via Travelling Waves
Hofbauer, J. (1998) · Springer eBooks · doi:10.1007/978-94-017-1654-3_20 · Cited by 13
CAN WELFARE POLICY MAKE USE OF SOCIAL NORMS?
Bird, E. J. (1999) · Rationality and Society · doi:10.1177/104346399011003004 · Cited by 16
What's a face worth: Noneconomic factors in game playing
Hancock, P., & DeBruine, L. M. (2003) · Behavioral and Brain Sciences · doi:10.1017/s0140525x03320059 · Cited by 17
Errors can increase cooperation in finite populations
Zhang, H. (2017) · Games and Economic Behavior · doi:10.1016/j.geb.2017.10.023 · Cited by 15
“As a result, many economists have shifted their attention to an evolutionary perspective for more useful predictions (Binmore and Samuelson, 1992; Foster and Young, 1990; Fudenberg and Maskin, 1990; Kandori et al., 1993; Selten, 1991; Young, 1993).”
BackgroundEvolutionary Equilibrium with Forward-Looking PlayersPreprint
Blume, L. E. (1995) · RePEc: Research Papers in Economics · Cited by 14
Reinforcement learning and the power law of practice: some analytical results
Ianni, A. (2002) · ePrints Soton (University of Southampton) · Cited by 13
Coordination and turnout in large elections
Diermeier, D. A., & Mieghem, J. A. V. (2008) · Mathematical and Computer Modelling · doi:10.1016/j.mcm.2008.05.042 · Cited by 13
Learning from learning in economics
Marimon, R. (2012) · Cambridge University Press eBooks · doi:10.1017/cbo9781139052009.009 · Cited by 13
Metadata
- Authors
- Young, H. P.
- Corresponding author
- Young, H. Peyton
- ORCID
- Young, H. Peyton
- Venue
- Econometrica
- Publisher
- JSTOR
- Published
- 1993-01
- Volume
- 61
- Issue
- 1
- Pages
- 57
- ISSN
- 0012-9682 (ISSN-L)
- OpenAlex
- W2118994458
- Cited by
- 2,399
- References
- 20
- Citations by year
- 2026: 52 · 2025: 57 · 2024: 75 · 2023: 86 · 2022: 65 · 2021: 78 · 2020: 57 · 2019: 63 · 2018: 83 · 2017: 82 · 2016: 83 · 2015: 83 · 2014: 114 · 2013: 110 · 2012: 99
- FWCI
- 47.85
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Econometrica (publishedVersion)
- Oxford University Research Archive (ORA) (University of Oxford) (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Oxford University Research Archive (ORA) (University of Oxford) (submittedVersion)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Game Theory and Applications
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Experimental Behavioral Economics Studies
- Social Sciences › Sociology and Political Science › Evolutionary Game Theory and Cooperation
- Keywords
- coordination games, convention formation, stochastic stability, repeated games, incomplete information, bounded rationality, learning, equilibrium selection, common knowledge
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.