Aspiration learning in coordination games

DOI10.1137/110852462MaRDI QIDQ4920268zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Georgios C. Chasparis, Ari Arapostathis, Jeff S. Shamma

Publication date 16 May 2013

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1110.4412

zbMATH Keywords

aspiration learningcoordination gamesgame theory

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Learning and adaptive systems in artificial intelligence (68T05) Evolutionary games (91A22) Rationality and learning in game theory (91A26) Applications of game theory (91A80) Stochastic learning and adaptive control (93E35)

Abstract: We consider the problem of distributed convergence to efficient outcomes in coordination games through dynamics based on aspiration learning. Under aspiration learning, a player continues to play an action as long as the rewards received exceed a specified aspiration level. Here, the aspiration level is a fading memory average of past rewards, and these levels also are subject to occasional random perturbations. A player becomes dissatisfied whenever a received reward is less than the aspiration level, in which case the player experiments with a probability proportional to the degree of dissatisfaction. Our first contribution is the characterization of the asymptotic behavior of the induced Markov chain of the iterated process in terms of an equivalent finite-state Markov chain. We then characterize explicitly the behavior of the proposed aspiration learning in a generalized version of coordination games, examples of which include network formation and common-pool games. In particular, we show that in generic coordination games the frequency at which an efficient action profile is played can be made arbitrarily large. Although convergence to efficient outcomes is desirable, in several coordination games, such as common-pool games, attainability of fair outcomes, i.e., sequences of plays at which players experience highly rewarding returns with the same frequency, might also be of special interest. To this end, we demonstrate through analysis and simulations that aspiration learning also establishes fair outcomes in all symmetric coordination games, including common-pool games.

Recommendations

• WHEN ASPIRING AND RATIONAL AGENTS STRIVE TO COORDINATE
• Learning aspiration in repeated games
• The efficiency of observability and mutual linkage
• Convergence of aspirations and (partial) cooperation in the prisoner's dilemma
• Evolving aspirations and cooperation

Cited in

(12)

• Learning and sophistication in coordination games
• Aspiration adaptation in the ultimatum minigame.
• Aspiration-based and reciprocity-based rules in learning dynamics for symmetric normal-form games
• Convergence of aspirations and (partial) cooperation in the prisoner's dilemma
• Measurement-based efficient resource allocation with demand-side adjustments
• WHEN ASPIRING AND RATIONAL AGENTS STRIVE TO COORDINATE
• The efficiency of observability and mutual linkage
• scientific article; zbMATH DE number 2000817 (Why is no real title available?)
• scientific article; zbMATH DE number 1881099 (Why is no real title available?)
• On learning dynamics underlying the evolution of learning rules
• Logit-Q dynamics for efficient learning in stochastic teams
• Mean-field games with finitely many players: independent learning and subjectivity

This page was built for publication: Aspiration learning in coordination games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4920268)