Learning to signal: Analysis of a micro-level reinforcement model

DOI10.1016/J.SPA.2008.02.014MaRDI QIDQ1004397zbMATH OpenOpenAlexFDO

Authors Raffaele Argiento, Robin Pemantle, Brian Skyrms, Stanislav Volkov

Publication date 10 March 2009

Published in Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL https://lup.lub.lu.se/record/4588099

zbMATH Keywords

evolutionary game theoryGame theoryincomplete informationsignalingurn model

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) 2-person games (91A05) Signaling and communication in game theory (91A28)

Review text

In a two player game theoretic setup, the authors consider the situation in which player one can observe a private signal, and player two's objective is to guess the signal correctly. Player one can transmit information about the signal, using an urn scheme, in which correct transmission, i.e. successful coordination, is reinforced. The authors show, that the urn scheme achieves asymptotically optimal coordination.

Recommendations

• On salience and signaling in sender-receiver games: partial pooling, learning, and focal points
• Learning to signal in a dynamic world
• scientific article; zbMATH DE number 1189215
• Learning and type compatibility in signaling games
• Evolutionary learning in signalling games

Cites work

• A dynamic model of social network formation
• A survey of random processes with reinforcement
• Asymptotics of a matrix valued Markov chain arising in sociology.
• Evolutionarily stable strategies and game dynamics
• scientific article; zbMATH DE number 1405930 (Why is no real title available?)
• Nonconvergence to unstable points in urn models and stochastic approximations
• On Sequential Designs for Maximizing the Sum of n Observations
• Stochastic algorithms
• The Randomized Play-the-Winner Rule in Medical Trials
• Time to absorption in discounted reinforcement models.
• Vertex-reinforced random walk on \(\mathbb Z\) has finite range

Cited in

(17)

• Evolutionary game theory: a renaissance
• The evolution of compositionality in signaling games
• Compositional signaling in a complex world
• David Lewis in the lab: experimental results on the emergence of meaning
• On salience and signaling in sender-receiver games: partial pooling, learning, and focal points
• Bidirectional optimization from reasoning and learning in games
• Evolutionary dynamics of Lewis signaling games: Signaling systems vs. partial pooling
• Some dynamics of signaling games
• Signaling games. Dynamics of evolution and learning
• Pragmatics, Logic and Information Processing
• The role of forgetting in the evolution and learning of language
• Wisdom of crowds versus groupthink: learning in groups and in isolation
• Inventing new signals
• Stein's method for the beta distribution and the Pólya-Eggenberger urn
• How signaling conventions are established
• Probe and adjust in information transfer games
• Emergence of information transfer by inductive learning

This page was built for publication: Learning to signal: Analysis of a micro-level reinforcement model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1004397)