Training multi-agent teams from zero knowledge with the competitive coevolutionary team-based particle swarm optimiser

A new competitive coevolutionary team-based particle swarm optimiser (CCPSO(t)) algorithm is developed to train multi-agent teams from zero knowledge. The CCPSO(t) algorithm is applied to train a team of agents to play simple soccer. The algorithm uses the charged particle swarm optimiser in a compe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Soft computing (Berlin, Germany) Ročník 20; číslo 2; s. 607 - 620
Hlavní autoři: Scheepers, Christiaan, Engelbrecht, Andries P.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2016
Springer Nature B.V
Témata:
Algorithms
Artificial Intelligence
Charged particles
Clustering
Computational Intelligence
Control
Convergence
Engineering
Hypotheses
Knowledge
Mathematical Logic and Foundations
Mechatronics
Methodologies and Application
Multiagent systems
Neural networks
Performance measurement
Robotics
Soccer
Teams
Training
Multi-agent system
Neural networks
Competitive coevolution
Zero knowledge
Simple soccer
Charged particle swarm optimiser
Cooperative coevolution
ISSN:1432-7643, 1433-7479
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A new competitive coevolutionary team-based particle swarm optimiser (CCPSO(t)) algorithm is developed to train multi-agent teams from zero knowledge. The CCPSO(t) algorithm is applied to train a team of agents to play simple soccer. The algorithm uses the charged particle swarm optimiser in a competitive and cooperative coevolutionary training environment to train neural network controllers for the players. The CCPSO(t) algorithm makes use of the FIFA league ranking relative fitness function to gather detailed performance metrics from each game played. The training performance and convergence behaviour of the particle swarm are analysed. A hypothesis is presented that explains the lack of convergence in the particle swarms. After applying a clustering algorithm on the particle positions, a detailed visual and quantitative analysis of the player strategies is presented. The final results show that the CCPSO(t) algorithm is capable of evolving complex gameplay strategies for a complex non-deterministic game.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-014-1525-0