One Swarm per Queen: A Particle Swarm Learning for Stochastic Games

Alain Tcheukam, Hamidou Tembine

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This article examines a particle swarm collaborative model-free learning algorithm for approximating equilibria of stochastic games with continuous action spaces. The results support the argument that a simple learning algorithm which consists to explore the continuous action set by means of multi-population of particles can provide a satisfactory solution. A collaborative learning between the particles of the same player takes place during the interactions of the game, in which the players and the particles have no direct knowledge of the payoff model. Each particle is allowed to observe her own payoff and has only one-step memory. The existing results linking the outcomes to stationary satisfactory set do not apply to this situation because of continuous action space and non-convex local response. We provide a different approach to stochastic differential inclusion for arbitrary number of agents.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2016
EditorsGiacomo Cabri, Gauthier Picard, Niranjan Suri
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages144-145
Number of pages2
ISBN (Electronic)9781509035342
DOIs
StatePublished - Dec 5 2016
Event10th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2016 - Augsburg, Germany
Duration: Sep 12 2016Sep 16 2016

Publication series

NameProceedings - IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2016

Other

Other10th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2016
CountryGermany
CityAugsburg
Period9/12/169/16/16

Keywords

  • Energy markets
  • Particle Swarm
  • Stochastic Games

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Control and Optimization

Fingerprint Dive into the research topics of 'One Swarm per Queen: A Particle Swarm Learning for Stochastic Games'. Together they form a unique fingerprint.

Cite this