Stigmergy in multi-agent reinforcement learning - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2004

Stigmergy in multi-agent reinforcement learning

Raghav Aras
  • Function : Author
  • PersonId : 830439
Alain Dutech

Abstract

In this paper, we describe how certain aspects of the biological phenomena of stigmergy can be imported into multi-agent reinforcement learning (MARL), with the purpose of better enabling coordination of agent actions and speeding up learning. In particular, we detail how these stigmergic aspects can be used to define an inter-agent communication framework.
Fichier principal
Vignette du fichier
arasr_stigmergy_136.pdf (31.93 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00000209 , version 1 (13-09-2005)

Identifiers

Cite

Raghav Aras, Alain Dutech, François Charpillet. Stigmergy in multi-agent reinforcement learning. Fourth International Conference on Hybrid Intelligent Systems - HIS'04, Dec 2004, Kitakyushu/Japan, pp.468-469, ⟨10.1109/ICHIS.2004.87⟩. ⟨inria-00000209⟩
150 View
278 Download

Altmetric

Share

More