CS344M Autonomous Multiagent Systems Todd Hester Department of - - PowerPoint PPT Presentation

▶
cs344m autonomous multiagent systems
SMART_READER_LITE
LIVE PREVIEW

CS344M Autonomous Multiagent Systems Todd Hester Department of - - PowerPoint PPT Presentation

Dec 23, 2023 125 likes •333 views

CS344M Autonomous Multiagent Systems Todd Hester Department of Computer Science The University of Texas at Austin Good Afternoon, Colleagues Are there any questions? How does a parasite go extinct? Todd Hester Logistics Executable

slide-1
SLIDE 1

CS344M Autonomous Multiagent Systems

Todd Hester Department of Computer Science The University of Texas at Austin

slide-2
SLIDE 2

Good Afternoon, Colleagues

Are there any questions?

  • How does a parasite go extinct?

Todd Hester

slide-3
SLIDE 3

Logistics

  • Executable teams due next Tuesday
  • Final reports due on Thursday
  • Final tournament: Monday, December 17th, 2pm, BUR 136

Todd Hester

slide-4
SLIDE 4

Logistics

  • Executable teams due next Tuesday
  • Final reports due on Thursday
  • Final tournament: Monday, December 17th, 2pm, BUR 136
  • Readings for next week

Todd Hester

slide-5
SLIDE 5

Logistics

  • Executable teams due next Tuesday
  • Final reports due on Thursday
  • Final tournament: Monday, December 17th, 2pm, BUR 136
  • Readings for next week
  • My thesis defense

– Monday, 11:30 AM, ACES 3.408 – TEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains

Todd Hester

slide-6
SLIDE 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

Todd Hester

slide-7
SLIDE 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

Todd Hester

slide-8
SLIDE 8

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

Todd Hester

slide-9
SLIDE 9

Rosin and Belew

  • Co-evolve 2 populations: Evolve software (hosts) and test

suites (parasites)

  • “New genotypes arise to defeat old ones”

– Why not self-play?

Todd Hester

slide-10
SLIDE 10

Rosin and Belew

  • Co-evolve 2 populations: Evolve software (hosts) and test

suites (parasites)

  • “New genotypes arise to defeat old ones”

– Why not self-play?

  • Three techniques to help:

– Competitve Fitness Sharing

Todd Hester

slide-11
SLIDE 11

Rosin and Belew

  • Co-evolve 2 populations: Evolve software (hosts) and test

suites (parasites)

  • “New genotypes arise to defeat old ones”

– Why not self-play?

  • Three techniques to help:

– Competitve Fitness Sharing – Shared Opponent Sampling

Todd Hester

slide-12
SLIDE 12

Rosin and Belew

  • Co-evolve 2 populations: Evolve software (hosts) and test

suites (parasites)

  • “New genotypes arise to defeat old ones”

– Why not self-play?

  • Three techniques to help:

– Competitve Fitness Sharing – Shared Opponent Sampling – Hall of Fame

Todd Hester

slide-13
SLIDE 13

Rosin and Belew

  • Co-evolve 2 populations: Evolve software (hosts) and test

suites (parasites)

  • “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

Todd Hester

slide-14
SLIDE 14

Hosts and Parasites

  • What happens if a new individual can beat a previously

unbeatable parasite?

Todd Hester

slide-15
SLIDE 15

Hosts and Parasites

  • What happens if a new individual can beat a previously

unbeatable parasite?

  • Other ways to divide fitness appropriately?

Todd Hester

slide-16
SLIDE 16

Competitive Co-evolution

  • Could

we apply competitve co-evolution to robot soccer?

Todd Hester

slide-17
SLIDE 17

Competitive Co-evolution

  • Could

we apply competitve co-evolution to robot soccer?

  • What about agents having to work together as a team?

Todd Hester

slide-18
SLIDE 18

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?

Todd Hester

slide-19
SLIDE 19

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?

Todd Hester

slide-20
SLIDE 20

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?

Todd Hester