Comparing PSO structures to learn the game of checkers from zero knowledge

Franken, N.; Engelbrecht, Andries P.

doi:10.1109/cec.2003.1299580

Cited by 34 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The swarm consisted of 25 particles arranged in a 5 × 5 lattice. The Von Neumann [3] neighbourhood topology was chosen because it has been shown to be superior in related work [3], [18], [19]. The neighbourhood contains the 4 particles that surround the subject particle in the lattice.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Tournament Particle Swarm Optimization

Duminy

Engelbrecht

2007

2007 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

Abstract-This paper introduces Tournament Particle Swarm Optimization (PSO) as a method to optimize weights of game tree evaluation functions in a competitive environment using Particle Swarm Optimization. This method makes use of tournaments to ensure a fair evaluation of the performance of particles in the swarm, relative to that of other particles. The empirical work presented compares the performance of different tournament methods that can be applied to the Tournament PSO, with application to Checkers.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Franken and Engelbrecht [17] extended the work of Messerschmidt and Engelbrecht on TIC-TAC-TOE by analysing the effect of different PSO structures and neural network topologies on the learning performance. This work was also applied to CHECKERS [18], [19].…”

Section: A the Competitive Pso Algorithmmentioning

confidence: 99%

Tournament Particle Swarm Optimization

Duminy

Engelbrecht

2007

2007 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

show abstract

“…Franken and Engelbrecht [23,24] investigated two different approaches using PSO to evolve strategies, one is Binary PSO and the other is neural networks. Chio [25] integrated strategies from the prisoner's dilemma into the PSO algorithm.…”

Section: Introductionmentioning

confidence: 99%

PSO Algorithm for IPD Game

Wang¹

2012

IJCSIT

View full text Add to dashboard Cite

show abstract

“…ANN based agents are also evolved by Messerschmidt and Engelbrecht for playing Tic-tac-toe [6] and by Franken and Engelbrecht for playing checkers [7]. The agents act as the evaluation function for the leaf nodes in minim-max search of the game tree.…”

Section: Related Workmentioning

confidence: 99%

Survival by continuous learning in a dynamic multiple task environment

Mujtaba

Baig

2008

2008 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

Abstract-The ability to adapt or not when challenged with a dynamic, changing environment is what differentiates between survival and extinction of species. In this paper we present a machine learning method that allows agents in an environment with changing tasks to adapt and modify their behavior thus ensuring their survival. These agents do not get explicit information about the change in tasks. The learning mechanism ensures the presence of enough diversity in the agents so that they can restart learning if the previous learning stops to be effective and enough continuity in the system so that the agents can keep on learning if their task has not changed.

show abstract

Comparing PSO structures to learn the game of checkers from zero knowledge

Cited by 34 publications

References 7 publications

Tournament Particle Swarm Optimization

Tournament Particle Swarm Optimization

PSO Algorithm for IPD Game

Survival by continuous learning in a dynamic multiple task environment

Contact Info

Product

Resources

About