1 / 9

Improving Starcraft II Build Orders Using Variable-Length Genetic Algorithm

Improving Starcraft II Build Orders Using Variable-Length Genetic Algorithm. ECE 539 Final Project Andrew Wolfgram UW-Madison 2010. Objective. Design a genetic algorithm to create quick build orders for the real-time strategy (RTS) game Starcraft II. Motivation.

dot
Télécharger la présentation

Improving Starcraft II Build Orders Using Variable-Length Genetic Algorithm

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. Improving Starcraft II Build Orders Using Variable-Length Genetic Algorithm ECE 539 Final Project Andrew Wolfgram UW-Madison 2010

  2. Objective • Design a genetic algorithm to create quick build orders for the real-time strategy (RTS) game Starcraft II

  3. Motivation • Starcraft II is very popular – “national sport” in South Korea • “Rush” builds can perform very well • Combination of class work and recreation

  4. Existing Approaches • Trial and Error by Players • Example Protoss Rush Build • Pylon • Gateway • Assimilator • Pylon • Cybernetics Core • Stalker and Warpgate Research • Pylon • Gateway • Sentry • Gateway • Gateway • Pylon • Create Stalkers

  5. Plan • Use genetic algorithm to come up with good (quick) build orders to get to a certain number of a particular unit • Fitness function is a combination of proximity to goal (number of units) and execution time

  6. Difficulties • Build orders are not like Traveling Salesman • Do not know length of chromosome – support for variable length chromosomes needed • Game is complex – timing determined by resource gathering rates and must be calculated for each chromosome

  7. Data • Data has been gathered experimentally by members of Team Liquid • Available on Liquipedia

  8. Expected Results • New possibilities for rush builds • New options for existing rush builds that streamline player execution

  9. Questions and Contact • awolfgram@wisc.edu

More Related