Active Learning Strategies and Active Control of Complexity Growth in Naming Games - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Active Learning Strategies and Active Control of Complexity Growth in Naming Games

Abstract

Naming Games are models of the dynamic formation of lexical conventions in populations of agents. In this work we introduce new Naming Game strategies, using developmental and active learning mechanisms to control the growth of complexity. An information theoretical measure to compare those strategies is introduced, and used to study their impact on the dynamics of the Naming Game.
Fichier principal
Vignette du fichier
main.pdf (1.4 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01202654 , version 1 (23-09-2015)

Identifiers

  • HAL Id : hal-01202654 , version 1

Cite

William Schueller, Pierre-Yves Oudeyer. Active Learning Strategies and Active Control of Complexity Growth in Naming Games. the 5th International Conference on Development and Learning and on Epigenetic Robotics, Aug 2015, Providence, RI, United States. ⟨hal-01202654⟩

Collections

ENSTA INRIA INRIA2
216 View
159 Download

Share

Gmail Facebook Twitter LinkedIn More