Follow: Share:Share

Game Lab

Games provide competitive dynamic environments and are therefore an ideal domain for the study and application of computational intelligence.

CIS promotes student research through games competition and organizing research results (algorithms, codes, and manuals, etc.) into a central repository.

GAME SITES


Starcraft AI Competition


Fighting Game AI Competition


General Video Game AI Competition (GVGAI) Competition


Human vs. Computer Go Competition


Geometry Friends Game AI Competition


Car Racing


Ms. PacMan

The aim of this competition is to provide the best software controller for the game of Ms Pac-Man. This is a great challenge for computational intelligence, machine learning, and AI in general.
Unlike Pac-Man, Ms. Pac-Man is a non-deterministic game, and rather difficult for most human players.  As far as we know, nobody really knows how hard it is to develop an AI player for the game. The world record for a human player (on the original arcade version) currently stands at 921,360. Can anyone develop a software agent to beat that?
The Ms. Pac-Man competition will test the ability of computer-based players at the conference.  We are especially interested in players that use computational intelligence methods to address the problem, but the contest is open to any type of algorithm: you can hand-program it as much as you like.
The mode of interaction is as follows: about 15 times per second your program will be sent a pixel map of the Ms. Pac-Man window, and it then responds with an integer indicating the direction of the joystick.

Super Mario

The 2011 Mario AI Championship, the successor to the very successful 2010 Mario AI Competition, will run in association with several major international conferences focusing on computational intelligence and games. The competition will consist of three tracks: Gameplay, Learning, Level Generation and we are happy to announce the new Turing Test track, with partly overlapping organizers.

Unreal Tournament

Computers are superbly fast and accurate at playing games, but can they be programmed to be more fun to play - to play like you and me? People like to play against opponents who are like themselves - opponents with personality, who can surprise, who sometimes make mistakes, yet don't blindly make the same mistakes over and over. The BotPrize competition challenges programmers/researchers/hobbyists to create a bot for UT2004 (a first-person shooter) that can fool opponents into thinking it is another human player. The competition has been sponsored by 2K games since 2008, and the $5000 major prize is yet to be claimed.


StarCraft

The Expressive Intelligence Studio at UC Santa Cruz hosted a StarCraft competition at AIIDE 2010 as part of the conference program. The competition enabled academic researchers to evaluate their AI systems in a robust commercial RTS environment.  The competition was held in the weeks leading up to the conference. The final matches were shown live at the conference with commentary. Exhibition matches were also held between skilled human players and the top performing bots.

 


Past-Game Competitions

 


 

Game competition:

Student StarCraft AI Tournamenthttp://sscaitournament.com/

 

Organiser(s)-Affiliation(s):

Czech Technical University in Prague

 

Contact email:

certicky@agents.fel.cvut.cz

 

Short description:

Student StarCraft AI Tournament (SSCAIT) is an educational event, held annually since 2011. It serves as a challenging competitive environment mainly, but not only for students of Artificial Intelligence and Computer Science. Participants are submitting the bots programmed in C++ or Java using BWAPI to play 1v1 StarCraft matches.

 

Records:

Conference-website

Year-Month

Nb. of entries (except samples)

Up to 3 winners

(Main methods or related papers if known)

standalone event

2016

45

  • 1st, 82pts: Martin Rooijackers, University of Maastricht (Netherlands)
  • 2nd, 63pts: Wulibot, University of Southern California (USA)
  • 3rd, 54pts: Zia Bot, Ulsan National Institute of Science and Technology (South Korea)

standalone event

2015

46

  • 1st, 37pts: Martin Rooijackers, University of Maastricht (Netherlands)
  • 2nd, 35pts: Carsten Nielsen, Technical University of Denmark (Denmark)
  • 3rd, 34pts: Dave Churchill, University of Alberta (Canada)

standalone event

2014

42

  • 1st, 111pts: Martin Rooijackers, University of Maastricht (Netherlands)
  • 2nd, 96pts: Sören Klett, Universität Bielefeld (Germany)
  • 3rd, 96pts (including a loss against S. Klett): Dave Churchill, University of Alberta (Canada)

standalone event

2013

50

  • 1st, 190pts: Tomáš Vajda, Comenius University (Slovakia)
  • 2nd, 184pts: Sören Klett, Universität Bielefeld (Germany)
  • 3rd, 169pts: Dave Churchill, University of Alberta (Canada)

standalone event

2012

52

  • 1st: Matej Istenik, University od Zilina (Slovakia)
  • 2nd: Marcin Bartnicki, Gdansk University of Technology (Poland)
  • 3rd: Dave Churchill, University of Alberta (Canada)

standalone event

2011

50

  • 1st: Roman Danielis, Comenius University (Slovakia)


Game competition:

The Fighting Game AI Competition – http://www.ice.ci.ritsumei.ac.jp/~ftgaic/

 

Organiser(s)-Affiliation(s):

Mainly by Ruck Thawonmas – College of Information Science and Engineering, Ritsumeikan University

 

Contact email:

ruck@is.ritsumei.ac.jp

 

Short description:

Participants develop their AI controllers for Java based fighting game "FightingICE". The competition and platform are organized and maintained by Intelligent Computer Entertainment Lab, College of Information Science and Engineering, Ritsumeikan University in Japan.

 

Major sample AIs:

2014: MizunoAI having an opponent modelling mechanism based on the k nearest neighbour algorithm

Kaito Yamamoto, Syunsuke Mizuno, Chun Yin Chu and Ruck Thawonmas, "Deduction of Fighting-Game Countermeasures Using the k-Nearest Neighbor Algorithm and a Game Simulator," Proc. of 2014 IEEE Conference on Computational Intelligence and Games (CIG 2014), Dortmund, Germany, pp. 437-441, Aug. 26-29, 2014.

2015: JerryMizunoAI combining MizunoAI with fuzzy rules

2016: MctsAi using Monte-Carlo tree search (MCTS)

Makoto Ishihara, Taichi Miyazaki, Chun Yin Chu, Tomohiro Harada, and Ruck Thawonmas, "Applying and Improving Monte-Carlo Tree Search in a Fighting Game AI," Proc. of the 13th International Conference on Advances in Computer Entertainment Technology (ACE 2016), Osaka, Japan, Nov. 9-12, 2016. DOI: http://dx.doi.org/10.1145/3001773.3001797

 

Records:

Conference-website

Year-Month

Nb. of entries (except samples)

Up to 3 winners

(Main methods or related papers if known)

http://www.ice.ci.ritsumei.ac.jp/~ftgaic/index-R.html

CIG 2016

2016-Sep.

13

1st : MCTS+ rule-based strategies

2nd: MCTS+ rule-based strategies

3 rd: MCTS+ rule-based strategies

http://www.ice.ci.ritsumei.ac.jp/~ftgaic/index-R15.html

CIG 2015

2015-Sep.

17

1st : rule-based strategies

2nd: finite state machine

3 rd: rule-based strategies

http://www.ice.ci.ritsumei.ac.jp/~ftgaic/index-R14.html

CIG 2014

2014-Aug.

18

(10 for one-character-type track; 8 for three-character-type track

One character track

1st : dynamic scripting

K. Majchrzak, J. Quadflieg, and G. Rudolph, "Advanced Dynamic Scripting for Fighting Game AI," Proc. of Entertainment Computing (ICEC 2015), pp. 86-99, 2015.

2nd: rule-based strategies

3 rd: finite state machine

Three character track

1st : finite state machine

2nd: rule-based strategies

3 rd: rule-based strategies with opponent modeling

http://www.ice.ci.ritsumei.ac.jp/~ftgaic/index-R13.html

2013-Oct.

10

1st : finite state machine

2nd: rule-based strategies

3 rd: rule-based strategies