The Mario AI Championship 2009-2012

We give a brief overview of the Mario AI Championship, a series of competitions based on an open source clone of the seminal platform game Super Mario Bros. The competition has four tracks. The gameplay and learning tracks resemble traditional reinforcement learning competitions, the Level generation track focuses on the generation of entertaining game levels, and the Turing Test track focuses on humanlike game-playing behavior. We also outline some lessons learned from the competition and its future. The article is written by the four organizers of the competition.

[1]  Erek R. Speed.  Evolving a Mario agent using cuckoo search and softmax heuristics , 2010, 2010 2nd International IEEE Consumer Electronics Society's Games Innovations Conference.

[2]  Anthony Brabazon,et al.  Evolving Behaviour Trees for the Mario AI Competition Using Grammatical Evolution , 2011, EvoApplications.

[3]  Zahid Halim,et al.  Measuring entertainment and automatic generation of entertaining games , 2010, Int. J. Inf. Technol. Commun. Convergence.

[4]  Julian Togelius,et al.  Mario AI competition , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[5]  Michael L. Littman,et al.  Planning in Reward-Rich Domains via PAC Bandits , 2012, EWRL.

[6]  Philip Hingston,et al.  A new design for a Turing Test for Bots , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[7]  Julian Togelius,et al.  The 2009 Simulated Car Racing Championship , 2010, IEEE Transactions on Computational Intelligence and AI in Games.

[8]  Julian Togelius,et al.  The turing test track of the 2012 Mario AI Championship: Entries and evaluation , 2013, 2013 IEEE Conference on Computational Inteligence in Games (CIG).

[9]  Jyh-Jong Tsay,et al.  Evolving Intelligent Mario Controller by Reinforcement Learning , 2011, 2011 International Conference on Technologies and Applications of Artificial Intelligence.

[10]  Clare Bates Congdon,et al.  REALM: A rule-based evolutionary computation agent that learns to play Mario , 2010, Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games.

[11]  Julian Togelius,et al.  The Mario AI Benchmark and Competitions , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[12]  Simon M. Lucas,et al.  Ms Pac-Man competition , 2007, SEVO.

[13]  J. Andrew Bagnell,et al.  Efficient Reductions for Imitation Learning , 2010, AISTATS.

[14]  William V. Wright,et al.  A Theory of Fun for Game Design , 2004 .

[15]  Risto Miikkulainen,et al.  Evolving Multimodal Networks for Multitask Games , 2012, IEEE Transactions on Computational Intelligence and AI in Games.

[16]  Yuichi Sato,et al.  Autonomously Acquiring a Video Game Agent's Behavior: Letting Players Feel Like Playing with a Human Player , 2012, Advances in Computer Entertainment.

[17]  Hiroharu Kawanaka,et al.  Search Algorithm with Learning Ability for Mario AI -- Combination A* Algorithm and Q-Learning , 2012, 2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing.

[18]  Julian Togelius,et al.  The 2010 Mario AI Championship: Level Generation Track , 2011, IEEE Transactions on Computational Intelligence and AI in Games.

[19]  Julian Togelius,et al.  The 2009 Mario AI Competition , 2010, IEEE Congress on Evolutionary Computation.

[20]  Hisashi Handa.  Dimensionality reduction of scene and enemy information in Mario , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).