Difference between revisions of "AIUR"

 
(2 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
|id=AIUR
 
|id=AIUR
 
|author=Florian Richoux
 
|author=Florian Richoux
|affiliation=
+
|affiliation=Université de Nantes
 
|country=France
 
|country=France
 
|country2=
 
|country2=
Line 13: Line 13:
 
|externalDownload=
 
|externalDownload=
 
|language=C++
 
|language=C++
|sourceCode=https://github.com/AIUR-group/AIUR
+
|github=https://github.com/AIUR-group/AIUR
 
|site=http://aiur-group.github.io/AIUR/
 
|site=http://aiur-group.github.io/AIUR/
 
|tlstream=
 
|tlstream=
Line 54: Line 54:
 
==Scientific papers==
 
==Scientific papers==
 
* Santiago Ontañón, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill and Mike Preuss. [http://pagesperso.lina.univ-nantes.fr/~richoux-f/publications/tciaig13.pdf A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft, Transactions on Computational Intelligence and AI in Games], IEEE, 2013.
 
* Santiago Ontañón, Gabriel Synnaeve, Alberto Uriarte, Florian Richoux, David Churchill and Mike Preuss. [http://pagesperso.lina.univ-nantes.fr/~richoux-f/publications/tciaig13.pdf A Survey of Real-Time Strategy Game AI Research and Competition in StarCraft, Transactions on Computational Intelligence and AI in Games], IEEE, 2013.
 +
 +
==Videos==
 +
{{#ev:youtube|sb8VtBnAK2M}}
 +
{{#ev:youtube|HJSjcIVvhVU}}
 +
{{#ev:youtube|ehDDTT0wsC4}}

Latest revision as of 11:16, 16 July 2015

[e][h]Picon.png AIUR
Author(s):
Florian Richoux
Affiliation:
Université de Nantes
Country:
France France
Race:
ELO peak:
BWAPI version:
3.7.4
Type:
DLL
Download:
Language:
C++
Source code:
Github.png
Links

AIUR (Artificial Intelligence Using Randomness) is an AI for StarCraft: Brood War, written by Florian Richoux.

The main idea is to be unpredictable by making some stochastic choices. The AI starts a game with a "mood" randomly picked up among 5 moods, dictating some behaviors (aggressive, fast expand, macro-game, ...). In addition, some other choices (productions, timing attacks, early aggressions, ...) are also taken under random conditions.

Learning is an essential part of AIUR. For this, it uses persistent I/O files system to record which moods are efficient against a given opponent, in order to modify the probability distribution for the mood selection.

Facts

  • One of the most popular bots to play because of its multiple build orders.
  • It uses Gateway units a lot.

Strategies

General

  • Cannon rush.
  • Perfectly timed maximum supply gateway timing.

Achievements

Scientific papers

Videos