1 / 126

Genetic Algorithms

Genetic Algorithms. Chapter 9, Complexity: A Guided Tour. Evolution by Natural Selection. Charles Darwin. Evolution by Natural Selection. Organisms inherit traits from parents. Charles Darwin. Evolution by Natural Selection. Organisms inherit traits from parents

xannon
Download Presentation

Genetic Algorithms

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. Genetic Algorithms Chapter 9, Complexity: A Guided Tour

  2. Evolution by Natural Selection Charles Darwin

  3. Evolution by Natural Selection • Organisms inherit traits from parents Charles Darwin

  4. Evolution by Natural Selection • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination Charles Darwin

  5. Evolution by Natural Selection • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination • Due to competition for limited resources, the organisms best adapted to the environment tend to produce the most offspring. Charles Darwin

  6. Evolution by Natural Selection • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination • Due to competition for limited resources, the organisms best adapted to the environment tend to produce the most offspring. • This way traits producing adapted individuals spread in the population Charles Darwin

  7. Evolution by Natural Selection in computers • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination • Due to competition for limited resources, the organisms best adapted to the environment tend to produce the most offspring. • This way traits producing adapted individuals spread in the population Computer (e.g., programs) Charles Darwin

  8. Evolution by Natural Selection in computers • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination • Due to competition for limited resources, the organisms best adapted to the environment tend to produce the most offspring. • This way traits producing adapted individuals spread in the population Computer (e.g., programs) Charles Darwin John Holland

  9. Evolution by Natural Selection in computers • Organisms inherit traits from parents • Traits are inherited with some variation, via mutation and sexual recombination • Due to competition for limited resources, the organisms best adapted to the environment tend to produce the most offspring. • This way traits producing adapted individuals spread in the population Computer (e.g., programs) Charles Darwin Genetic Algorithms (GAs) John Holland

  10. Some real-world uses of genetic algorithms

  11. Some real-world uses of genetic algorithms • Used by GE to automate parts of aircraft design

  12. Some real-world uses of genetic algorithms • Used by GE to automate parts of aircraft design • Used by pharmaceutical companies to discover new drugs

  13. Some real-world uses of genetic algorithms • Used by GE to automate parts of aircraft design • Used by pharmaceutical companies to discover new drugs • Used by the London Stock Exchange to automatically detect fraudulent trades

  14. Some real-world uses of genetic algorithms • Used by GE to automate parts of aircraft design • Used by pharmaceutical companies to discover new drugs • Used by the London Stock Exchange to automatically detect fraudulent trades • Used to generate realistic computer animation in the movies Lord of the Rings: The Return of the King and Troy

  15. Some real-world uses of genetic algorithms • Used by GE to automate parts of aircraft design • Used by pharmaceutical companies to discover new drugs • Used by the London Stock Exchange to automatically detect fraudulent trades • Used to generate realistic computer animation in the movies Lord of the Rings: The Return of the King and Troy • Used to model and understand evolution in nature!

  16. Example: Evolving Strategies for Robby the Robot

  17. Example: Evolving Strategies for Robby the Robot Input: Contents of N, S, E, W, C(Current)

  18. Example: Evolving Strategies for Robby the Robot Input: Contents of N, S, E, W, C(Current) Possible actions: Move N Move S Move E Move W Move random Stay put Try to pick up can

  19. Example: Evolving Strategies for Robby the Robot Input: Contents of N, S, E, W, C(Current) Possible actions: Move N Move S Move E Move W Move random Stay put Try to pick up can Rewards/Penalties (points): Picks up can: 10 Tries to pick up can on empty site: -1 Crashes into wall: -5

  20. Example Strategy

  21. Encoding a Strategy Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  22. Encoding a Strategy Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  23. Encoding a Strategy 0 Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  24. Encoding a Strategy 0 2 Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  25. Encoding a Strategy 0 2 6 Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  26. Encoding a Strategy 0 2 6 5 . . . 3 . . . 4 Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  27. Encoding a Strategy 243 values 0 2 6 5 . . . 3 . . . 4 Code: MoveNorth = 0 MoveSouth = 1 MoveEast = 2 MoveWest = 3 StayPut = 4 PickUpCan = 5 MoveRandom = 6

  28. Genetic algorithm for evolving strategies for Robby

  29. Genetic algorithm for evolving strategies for Robby • Generate 200 random strategies (i.e., programs for controlling Robby)

  30. Random Initial Population

  31. Genetic algorithm for evolving strategies for Robby • Generate 200 random strategies (i.e., programs for controlling Robby) • For each strategy, calculate fitness (average reward minus penalties earned on random environments)

  32. Genetic algorithm for evolving strategies for Robby • Generate 200 random strategies (i.e., programs for controlling Robby) • For each strategy, calculate fitness (average reward minus penalties earned on random environments) • The strategies pair up and create offspring via “sexual recombination” with random mutations ― the fitter the parents, the more offspring they create.

  33. Parent 1: Parent 2:

  34. Parent 1: Parent 2:

  35. Parent 1: Parent 2: Child:

  36. Genetic algorithm for evolving strategies for Robby • Generate 200 random strategies (i.e., programs for controlling Robby) • For each strategy, calculate fitness (average reward minus penalties earned on random environments) • The strategies pair up and create offspring via “sexual recombination” with random mutations ― the fitter the parents, the more offspring they create. • Keep going back to step 2 until a good-enough strategy is found!

  37. My hand-designed strategy:

  38. My hand-designed strategy: “If there is a can in the current site, pick it up.”

  39. My hand-designed strategy: “If there is a can in the current site, pick it up.” “Otherwise, if there is a can in one of the adjacent sites, move to that site.”

  40. My hand-designed strategy: “If there is a can in the current site, pick it up.” “Otherwise, if there is a can in one of the adjacent sites, move to that site.” “Otherwise, choose a random direction to move in.”

  41. My hand-designed strategy: “If there is a can in the current site, pick it up.” “Otherwise, if there is a can in one of the adjacent sites, move to that site.” “Otherwise, choose a random direction to move in.” Average fitness of this strategy: 346 (out of max possible  500)

  42. My hand-designed strategy: “If there is a can in the current site, pick it up.” “Otherwise, if there is a can in one of the adjacent sites, move to that site.” “Otherwise, choose a random direction to move in.” Average fitness of this strategy: 346 (out of max possible  500) Average fitness of GA evolved strategy: 486 (out of max possible  500)

  43. My hand-designed strategy: “If there is a can in the current site, pick it up.” “Otherwise, if there is a can in one of the adjacent sites, move to that site.” “Otherwise, choose a random direction to move in.” Average fitness of this strategy: 346 (out of max possible  500) Average fitness of GA evolved strategy: 486 (out of max possible  500) ???

  44. One Run of the Genetic Algorithm Best fitness in population Generation number

  45. Generation 1 Best average score = 81

  46. Time: 0 Score: 0 0 1 23 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9

  47. Time: 1 Score: 0 0 1 23 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9

  48. Time: 2 Score: 5 0 1 23 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9

  49. Time: 2 Score: 5 0 1 23 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9

  50. Time: 3 Score: 10 0 1 23 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9

More Related