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

William Schueller 1 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
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.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.inria.fr/hal-01202654
Contributor : William Schueller <>
Submitted on : Wednesday, September 23, 2015 - 1:48:07 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:04 AM
Long-term archiving on : Tuesday, December 29, 2015 - 9:00:19 AM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01202654, version 1

Citation

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⟩

Share

Metrics

Record views

349

Files downloads

238