Optimizing Strategy Parameters in a Game Bot          A. Fernández-Ares, A.M. Mora, J.J. Merelo,          P. García-Sánche...
Agenda                Introduction                Problem description                Baseline: GoogleBot                Fi...
Introduction                Google AI Challenge                Planet Wars Gameviernes 10 de junio de 2011
viernes 10 de junio de 2011
Problem description                                                          Actions                              Current ...
Baseline: GoogleBot                Included in the framework to use as a comparator of                quality             ...
First Approach: AresBot                In each turn:                Select the base according a score function (the rest a...
AresBot parameters                titheperc and titheprob: percentage of starships the bot                sends/probabilit...
Operation GeneBot                Using intergalactic techniques from planet Ares to                evolve AresBot: a Genet...
Fitness Function                Each individual runs in five relevant maps                Ranked fitness:                   ...
Experiments                Population of 400 individuals                40 sec to evaluate each one, so just one evaluatio...
Results                              titheperc   titheprob   ωNS−DIS   ωGR        poolperc     supportperc supportprob    ...
Conclusions and          Future Work                GeneBot ended in 1454 position in the contest (36%).                10...
Thanks!          (and questions, I guess)viernes 10 de junio de 2011
Upcoming SlideShare
Loading in …5
×

Optimizing Strategy Parameters in a Game Bot

1,145 views

Published on

Using a GA to optimize a hand-coded bot to play Planet Wars game.

0 Comments
3 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
1,145
On SlideShare
0
From Embeds
0
Number of Embeds
254
Actions
Shares
0
Downloads
5
Comments
0
Likes
3
Embeds 0
No embeds

No notes for slide

Optimizing Strategy Parameters in a Game Bot

  1. 1. Optimizing Strategy Parameters in a Game Bot A. Fernández-Ares, A.M. Mora, J.J. Merelo, P. García-Sánchez, and C.M. Fernandesviernes 10 de junio de 2011
  2. 2. Agenda Introduction Problem description Baseline: GoogleBot First Approach: AresBot Second Approach: GeneBot Conclusionsviernes 10 de junio de 2011
  3. 3. Introduction Google AI Challenge Planet Wars Gameviernes 10 de junio de 2011
  4. 4. viernes 10 de junio de 2011
  5. 5. Problem description Actions Current Bot to status perform Restrictions RTS->Turn based game. A turn = 1 sec No memory to store knowledge about the game Current status: planets and fleets Actions: a text file with actions to be read by the gameviernes 10 de junio de 2011
  6. 6. Baseline: GoogleBot Included in the framework to use as a comparator of quality How does it work: Seeks the planet that hosts most ships (base) Target planet calculated using the ratio of growth-rate and number of ships Waits until the fleet reachs the targetviernes 10 de junio de 2011
  7. 7. First Approach: AresBot In each turn: Select the base according a score function (the rest are colonies) Select a target planet to attack For each colony: Reinforcement of base planet (tithe) or Contribute to attackingviernes 10 de junio de 2011
  8. 8. AresBot parameters titheperc and titheprob: percentage of starships the bot sends/probability it happens. ωNS−DIS and ωGR: weight of the number of starships, distance to target from base and planet growth rate (used in the score function of target planet) poolperc and supportperc: percentage ships that the bot sends from the base planet or colonies to the target planet. supportprob: probability of sending extra fleets from the colonies to the target planetviernes 10 de junio de 2011
  9. 9. Operation GeneBot Using intergalactic techniques from planet Ares to evolve AresBot: a Genetic Algorithm! Gene: parameters array 2-Tournament BLX-alpha crossover Ellitismviernes 10 de junio de 2011
  10. 10. Fitness Function Each individual runs in five relevant maps Ranked fitness: LT: Number of games a bot wins if equal-> WT: number of turns to winviernes 10 de junio de 2011
  11. 11. Experiments Population of 400 individuals 40 sec to evaluate each one, so just one evaluation to enter in the competition (4 hours per generation)->(yes, parallelism in future...)viernes 10 de junio de 2011
  12. 12. Results titheperc titheprob ωNS−DIS ωGR poolperc supportperc supportprob AresBot 0,1 0,5 1 1 0,25 0,5 0,9 GeneBot 0,294 0,0389 0,316 0,844 0,727 0,822 0,579 Turns Victories Average and Std. Dev. Min Max AresBot 210 ± 130 43 1001 99 GeneBot 159 ± 75 22 458 100viernes 10 de junio de 2011
  13. 13. Conclusions and Future Work GeneBot ended in 1454 position in the contest (36%). 1000 positions better than AresBot More work to do: Paralellism Multi-objective approachs Genetic Programming Stop when the bot acquire self-awareness, of course.viernes 10 de junio de 2011
  14. 14. Thanks! (and questions, I guess)viernes 10 de junio de 2011

×