1 / 22

Dynamic Task Allocation in a turn based strategy game

Dynamic Task Allocation in a turn based strategy game. Gilles Schtickzelle September 2012 ULB. Problem Statement. Creating an intelligent player for a turn-based strategy game. Working Framework: Many possible challenges to meet: Resource management Adversarial planning Spatial reasoning

waneta
Download Presentation

Dynamic Task Allocation in a turn based strategy game

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. Dynamic Task Allocation in a turn based strategy game Gilles Schtickzelle September 2012 ULB

  2. Problem Statement • Creating an intelligent player for a turn-based strategy game. • Working Framework: • Many possible challenges to meet: • Resource management • Adversarial planning • Spatial reasoning • …

  3. A game of FreeCol • Colonization of America • Establish settlements, grow and develop them • Victory: Declare independence & Beat the Royal Expeditionary Force

  4. Colony Management • Assigning tasks to units for optimal resources production

  5. Division of labor in insect societies • Ants and wasps colonies have efficient distributed task allocation mechanisms through stygmergy. Bonabeau, E., Theraulaz, G., & Deneubourg, J.-L. (1996).

  6. Response Threshold • Ants have probabilistic response to stimuli: • Varying threshold θ induces specialization • Reduces switching costs • Increases individual efficiency

  7. From insects to games • Ants/Wasps Colony • Insects • Tasks • Specialization • FreeCol Colony • Units • Resources • Expert units

  8. Resources Dynamics • Surplus: Extra workers. Shortage: Loseworker. • Freedom. 50% required to win. Gives bonus or penalty to workers. • required to makehammers • Used to produce buildings or artileries • required to maketools • Used to produce buildings or artilleries

  9. Allocation Mechanism • One stimulus Sr for each resource r = • One set of dynamic thresholds θriper unit i

  10. Stimuli and Thresholds • Simple computation rules for each stimulus • One set of dynamic thresholds θruper unit u • GeneticAlgorithm to findappropriatescalefactorsβr

  11. Simple Scenario

  12. AI goals • Reach the year 1776 with enough bells to be able to declare independence. • Have the best defense possible to resist the attack of the royal expeditionary force. • Allocate workers to • minimize famine • Keep the production modifier as high as possible

  13. Results (Basic player)

  14. Planning approach • Suboptimal allocation: building too early • Two planning methods: • Layered response threshold. • Rule-based planning.

  15. Planning approach • Layered response threshold : • Use two sets of scalefactors: • Optimized for growth • Optimized for production • Rule-based planning :

  16. Planning Results (1) Layered AI Rule-based AI

  17. Planning Results (2) Statistics for 100 gameswith the simple scenario.

  18. Modified Threshold rule • Unit u produces resource r • Unit u does not produces resource r

  19. “State of the art” player • Modified Threshold update rule + rule-based planning

  20. AI players comparison

  21. AI goal completion • Reach the year 1776 with enough bells to be able to declare independence. • Have the best defense possible to resist the attack of the royal expeditionary force. • Allocate workers to • minimize famine • Keep the production modifier has high as possible

  22. Conclusions • Human-level performances can emerge from simple rules, without cheating. • Easy to implement (compared to traditional rule-based only AI). • Easy to tune down performances (if playing against non-expert). • Hybrid system (with planning instructions) improves on basic RTM • Tendency to chaos with large number of stimuli • Difficult to extend to other game aspects (combat, spatial reasoning, diplomacy,…).

More Related