1 / 27

Blondie24

Blondie24. Presented by Adam Duffy and Josh Hill. Overview. Introduction to new concepts Design of Blondie24 Testing and results Other approaches to checkers Other approaches to evolutionary computation Why is this important?. Neural Networks. Nodes connected by links Input nodes

mircea
Download Presentation

Blondie24

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Blondie24 Presented by Adam Duffy and Josh Hill

  2. Overview • Introduction to new concepts • Design of Blondie24 • Testing and results • Other approaches to checkers • Other approaches to evolutionary computation • Why is this important?

  3. Neural Networks • Nodes connected by links • Input nodes • Hidden nodes • Output nodes • Links have weights

  4. Evolutionary Computation • Based on natural selection • Initialize population • Fitness function • Selection • Cross-over • Mutation

  5. Design of Blondie24 • Checkers neural network • Values for input nodes • Red – positive • White – negative • Empty – zero • Piece differential

  6. Design of Blondie24 • Connections between squares • Subsections

  7. Design of Blondie24 • Search methods • Minimax • Alpha-beta pruning • Iterative deepening • Quiescent • Hash table of previously evaluated positions (maximum of 270,000)

  8. Design of Blondie24 • Initial population of 30 • Each neural network plays 5 games as red • +1 for a win • 0 for a draw • -2 for a loss • Top 15 kept, lowest 15 eliminated • Copy top 15 and mutate the weights

  9. Blondie24: Advantages • Can learn new strategies • Doesn’t have human biases

  10. Blondie24: Disadvantages • Long time • Doesn’t make use of expert knowledge

  11. Tests • 400 MHz Pentium II • 840th generation • Played games on zone.com • 165 games total (84 as red, 81 as white)

  12. Results • zone.com rating: 2045.85 • In top 500 of over 120,000 • Better than 99.61% of registered players

  13. Chinook • Primary feature - piece count • Looks for certain features • Over 40,000 opening lines of play • Every ending with <= 8 pieces • Higher value to positions with more pieces • Rated 2,814 at retirement in 1996

  14. Different Evolutionary Approach • Particle Swarm Optimizers (PSO) • Each particle is moved closer to • Global best • Personal best so far

  15. Other applications • Industry, medicine, and defense • Pattern recognition • Cancer

  16. More information • Blondie 24: Playing at the Edge of AI by David B. Fogel • Learning to play games using a PSO-based competitive learning approach by L. Messeischmidt and A.P. Engelbrecht • The Advantages of Evolutionary Computation by David B. Fogel • Solving the Game of Checkers by Jonathan Schaeffer and Robert Lake

More Related