1 / 8

M ario AI

M ario AI. Level Generation Track. Competition Goals. Create an automatic level generator for Infinite Mario Bros. Levels should be randomly generated based on certain input values Terrain type Difficulty Replayed levels should be regenerated, never the same as before.

monifa
Download Presentation

M ario AI

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. MarioAI Level Generation Track

  2. Competition Goals • Create an automatic level generator for Infinite Mario Bros. • Levels should be randomly generated based on certain input values • Terrain type • Difficulty • Replayed levels should be regenerated, never the same as before. • The winner will be decided through live play tests.

  3. Program Requirements • Must run on an Intel computer. • OS choices • Mac OSX - The preferred OS. • Ubuntu • Windows XP - Available via Windows 7 compatibility mode.

  4. Language Requirements • Any language is accepted. • Java is the preferred language. • For other languages : • They must be well commented. • Must interface to an unmodified version of the basic game package. • Must be runnable from an applet.

  5. Getting started • Basic packages are available and can be run without difficulty. • Source code from previous entrants is available. • Tutorials on running the agent are available from the website.

  6. How it works • Two main objects: • Test levels. • Customized levels. • Program uses test level to gather user data. • It then creates a customized level based on this data. • 2012 Competition has ended. • Entries have opened again.

  7. Future Program Use • Testing Learning Algorithms • Player’s playing style must be learned to generate a fun level for them. • Proceduralized Terrain Generation • Every time a level is loaded it must be randomly created.

  8. Links • Youtube example – • http://www.youtube.com/watch?v=lowW0HyZhTg • Mario Ai • http://www.marioai.org/LevelGeneration

More Related