Adaptive learning in large populations

DOI10.1007/S00285-019-01427-3MaRDI QIDQ2007697zbMATHOpenAlexWikidataFDO

Authors Mikhail Perepelitsa

Publication date 22 November 2019

Published in Journal of Mathematical Biology (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1901.02908

zbMATH Keywords

symmetric gamesadaptive learningrelative payoff sum

Mathematics Subject Classification ID

PDEs in connection with game theory, economics, social and behavioral sciences (35Q91) 2-person games (91A05) Multistage and repeated games (91A20)

Abstract: We consider the adaptive learning rule of Harley (1981) for behavior selection in symmetric conflict games in large populations. The rule uses organisms' past, accumulated rewards as the predictor for the future behavior, and can be traced in many life forms from bacteria to humans. We derive a partial differential equation (PDE) that describes the stochastic learning in a population of agents. The equation has simple structure of the `conservation of mass'-type equation in the space of stimuli to engage in a particular type of behavior. We analyze the solutions of the PDE model for typical 2x2 games. It is found that in games with small residual stimuli, adaptive learning rules with faster memory decay have an evolutionary advantage.

Recommendations

• Adaptive dynamics in games played by heterogeneous populations
• Learning, matching, and aggregation
• Stochastic adaptation in finite games played by heterogeneous populations
• On learning dynamics underlying the evolution of learning rules
• scientific article; zbMATH DE number 1189218

Cites work

• scientific article; zbMATH DE number 5869530 (Why is no real title available?)
• scientific article; zbMATH DE number 3152611 (Why is no real title available?)
• scientific article; zbMATH DE number 1233801 (Why is no real title available?)
• scientific article; zbMATH DE number 3109895 (Why is no real title available?)
• Evolutionarily stable strategies and game dynamics
• Heterogeneous beliefs and local information in stochastic fictitious play
• Interacting multiagent systems. Kinetic equations and Monte Carlo methods
• Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term
• Learning in games via reinforcement and regularization
• Learning through reinforcement and replicator dynamics
• Optimal properties of stimulus-response learning models.
• Reinforcement learning. An introduction
• Stochastic approximation algorithms with constant step size whose average is cooperative
• The Fokker-Planck equation. Methods of solution and applications
• The logic of animal conflict

Cited in

(5)

• Effective learning in the presence of adaptive counterparts
• LEARNING, EVOLUTION AND POPULATION DYNAMICS
• A model of cultural evolution in the context of strategic conflict
• On learning dynamics underlying the evolution of learning rules
• Spatial evolution of regularization in learned behavior of animals

This page was built for publication: Adaptive learning in large populations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2007697)