cs344m autonomous multiagent systems
play

CS344M Autonomous Multiagent Systems Patrick MacAlpine Department - PowerPoint PPT Presentation

CS344M Autonomous Multiagent Systems Patrick MacAlpine Department of Computer Science The University of Texas at Austin Good Afternoon, Colleagues Are there any questions? Patrick MacAlpine Logistics Progress reports due at beginning of


  1. CS344M Autonomous Multiagent Systems Patrick MacAlpine Department of Computer Science The University of Texas at Austin

  2. Good Afternoon, Colleagues Are there any questions? Patrick MacAlpine

  3. Logistics • Progress reports due at beginning of class Thursday − 2 hard copies − Attach your proposals − Anonymized soft copy Patrick MacAlpine

  4. Logistics • Progress reports due at beginning of class Thursday − 2 hard copies − Attach your proposals − Anonymized soft copy • Peer reviews due next Thursday Patrick MacAlpine

  5. Genetic Algorithms • Keep a population of individuals • Each generation: – Evaluate their fitness – Throw out the bad ones – Change the good ones randomly (crossover, mutation) – Repeat Patrick MacAlpine

  6. Genetic Algorithms • Keep a population of individuals • Each generation: – Evaluate their fitness – Throw out the bad ones – Change the good ones randomly (crossover, mutation) – Repeat The fitness function matters Patrick MacAlpine

  7. Genetic Algorithms • Keep a population of individuals • Each generation: – Evaluate their fitness – Throw out the bad ones – Change the good ones randomly (crossover, mutation) – Repeat The fitness function matters • Playing against top-notch competition -> no info • Playing against a single foe -> too brittle Patrick MacAlpine

  8. Rosin and Belew • Co-evolve 2 populations: Evolve software and test suites • “New genotypes arise to defeat old ones” – Why not self-play? Patrick MacAlpine

  9. Rosin and Belew • Co-evolve 2 populations: Evolve software and test suites • “New genotypes arise to defeat old ones” – Why not self-play? • Three techniques to help: – Competitve Fitness Sharing Patrick MacAlpine

  10. Rosin and Belew • Co-evolve 2 populations: Evolve software and test suites • “New genotypes arise to defeat old ones” – Why not self-play? • Three techniques to help: – Competitve Fitness Sharing – Shared Opponent Sampling Patrick MacAlpine

  11. Rosin and Belew • Co-evolve 2 populations: Evolve software and test suites • “New genotypes arise to defeat old ones” – Why not self-play? • Three techniques to help: – Competitve Fitness Sharing – Shared Opponent Sampling – Hall of Fame Patrick MacAlpine

  12. Rosin and Belew • Co-evolve 2 populations: Evolve software and test suites • “New genotypes arise to defeat old ones” – Why not self-play? • Three techniques to help: – Competitve Fitness Sharing – Shared Opponent Sampling – Hall of Fame • Tests on Nim and 3D Tic Tac Toe • Stop when perfect play is reached Patrick MacAlpine

  13. Competitive Co-evolution • Could we apply competitve co-evolution to robot soccer? Patrick MacAlpine

  14. Competitive Co-evolution • Could we apply competitve co-evolution to robot soccer? • What about agents having to work together as a team? Patrick MacAlpine

  15. Competitive Co-evolution • Could we apply competitve co-evolution to robot soccer? • What about agents having to work together as a team? • When to stop learning run? Patrick MacAlpine

  16. Competitive Co-evolution • Could we apply competitve co-evolution to robot soccer? • What about agents having to work together as a team? • When to stop learning run? • Examples of co-evolution in nature? Patrick MacAlpine

  17. Competitive Co-evolution • Could we apply competitve co-evolution to robot soccer? • What about agents having to work together as a team? • When to stop learning run? • Examples of co-evolution in nature? • Other approaches to competitive co-evolution? Patrick MacAlpine

Recommend


More recommend