21,266 Hits in 5.9 sec

How to Run a Successful Game-Based AI Competition

Julian Togelius
2016 IEEE Transactions on Computational Intelligence and AI in Games  
There is also a discussion of how to write up game-based AI competitions and what we can ultimately learn from them.  ...  Game-based competitions are commonly used within the Computational Intelligence (CI) and Artificial Intelligence (AI) in games community to benchmark algorithms and to attract new researchers.  ...  SUCCESS AND FAILURE Not all game-based AI competitions are equal: some have more impact than others. A competition may get no entrants, run only once, stagnate, or evolve and keep being relevant.  ... 
doi:10.1109/tciaig.2014.2365470 fatcat:pqn25zdnzvavbgs4lu4z4cjtqi

The Text-Based Adventure AI Competition [article]

Timothy Atkinson, Hendrik Baier, Tara Copplestone, Sam Devlin, Jerry Swan
2019 arXiv   pre-print
By providing a platform for evaluating agents in text-based adventures, the competition provides a novel benchmark for game AI with unique challenges for natural language understanding and generation.  ...  This competition fills a gap in existing game AI competitions that have typically focussed on traditional card/board games or modern video games with graphical interfaces.  ...  We would also like to thank Karthik Narasimhan and Tejas D. Kulkarni for their input when originally defining the format of the first competition.  ... 
arXiv:1808.01262v4 fatcat:6wmiuhg67redxixjmx35u7i4ea

General Video Game Playing

John Levine, Clare Bates Congdon, Marc Ebner, Graham Kendall, Simon M. Lucas, Risto Miikkulainen, Tom Schaul, Tommy Thompson, Michael Wagner
2013 Dagstuhl Publications  
We envisage running a competition based on GVGP playing, using arcade-style (e.g. similar to Atari 2600) games as our starting point.  ...  The AI player then has to work out how to play the game and how to win.  ...  game-playing agents tested via some form of long-running competition.  ... 
doi:10.4230/dfu.vol6.12191.77 dblp:conf/dagstuhl/LevineCEKLMST13 fatcat:ud7gsnfozfam5d5gtbkqbibemy

Towards Game-Playing AI Benchmarks via Performance Reporting Standards [article]

Vanessa Volz, Boris Naujoks
2020 arXiv   pre-print
The vision we describe is to build benchmarks and competitions based on such guidelines in order to be able to draw more general conclusions about the behaviour of different AI algorithms, as well as the  ...  As a result, it remains difficult to draw general conclusions about the strengths and weaknesses of different game-playing AI algorithms.  ...  Competitions can also be indirect, e.g in single-player games that have easily comparable metrics, such as the Angry Birds competition which ranks AI systems based on how many points they score when playing  ... 
arXiv:2007.02742v1 fatcat:syeql2jqhza7rebmgiw5gqt2d4

The 2017 AIBIRDS Competition [article]

Matthew Stephenson, Jochen Renz, Xiaoyu Ge, Peng Zhang
2018 arXiv   pre-print
This competition tasked participants with developing an intelligent agent which can play the physics-based puzzle game Angry Birds.  ...  Agents entered into this competition were required to solve a wide assortment of previously unseen levels within a set time limit.  ...  The General Video Game AI (GVGAI) Competition has also run several tracks around developing agents for playing general video games.  ... 
arXiv:1803.05156v1 fatcat:s3dhhhvtbrf6dnnvlssbzwqdjq

The 2009 Mario AI Competition

Julian Togelius, Sergey Karakovskiy, Robin Baumgarten
2010 IEEE Congress on Evolutionary Computation  
This paper describes the 2009 Mario AI Competition, which was run in association with the IEEE Games Innovation Conference and the IEEE Symposium on Computational Intelligence and Games.  ...  We conclude the paper by discussing what the outcomes of the competition can teach us both about developing platform game AI and about organizing game AI competitions.  ...  AI for platform games By far the most surprising outcome of the competition was how well the A*-based controllers performed compared to all other controller architectures, including controllers based on  ... 
doi:10.1109/cec.2010.5586133 dblp:conf/cec/TogeliusKB10 fatcat:w2blfnl6ozgu7dhlpgupttfruy

The Mario AI Benchmark and Competitions

Sergey Karakovskiy, Julian Togelius
2012 IEEE Transactions on Computational Intelligence and AI in Games  
This paper describes the Mario AI benchmark, a game-based benchmark for reinforcement learning algorithms and game AI techniques developed by the authors.  ...  The benchmark is based on a public domain clone of Nintendo's classic platform game Super Mario Bros, and completely open source.  ...  Compared to those papers, the current paper contains updated and technically deeper information on the benchmark, results from the 2010 competitions, descriptions of new entrants and tracks, and additional  ... 
doi:10.1109/tciaig.2012.2188528 fatcat:yllec7xwondqjhqtgh6fkmfpru

Game AI Competitions: Motivation for the Imitation Game-Playing Competition

Maciej Świechowski
2020 Proceedings of the 2020 Federated Conference on Computer Science and Information Systems  
This leads to multi-directional implications both on research and industry. In addition to the proposal, we include a short survey of the available game AI competitions.  ...  Games have played crucial role in advancing research in Artificial Intelligence and tracking its progress. In this article, a new proposal for game AI competition is presented.  ...  The next section is devoted to a short survey of the major modern competitions regarding game-based AI. In Section III, we present the motivation for the new competition.  ... 
doi:10.15439/2020f126 dblp:conf/fedcsis/Swiechowski20 fatcat:abhgqzwgrfaofd5sttasw3baae

Guest Editorial: Physics-Based Simulation Games

Jochen Renz, Risto Miikkulainen, Nathan R. Sturtevant, Mark H.M. Winands
2016 IEEE Transactions on Computational Intelligence and AI in Games  
He runs the Grid-Based Pathfinding Competition (GPPC) and his research was implemented in the commercial game Dragon Age: Origins.  ...  His scientific research interests include artificial intelligence and search in single-agent and multiagent settings, including applications to real-time environments, such as games, and more competitive  ...  Playing these games as well as or better than the best human players requires a successful AI agent to solve a number of challenging problems from different areas of AI.  ... 
doi:10.1109/tciaig.2016.2571560 fatcat:od5rgb6gizdvrm6ld3i6bm3juy

ColorShapeLinks: A Board Game AI Competition for Educators and Students

Nuno Fachada
2021 Computers and Education: Artificial Intelligence  
The competition is based on an arbitrarilysized version of the Simplexity board game, the motto of which, "simple to learn, complex to master", is curiously also applicable to AI agents.  ...  It has been successfully used for running internal competitions in AI classes, as well as for hosting an international AI competition at the IEEE Conference on Games.  ...  Acknowledgments This work is supported by Fundação para a Ciência e a Tecnologia under Grants UIDB/04111/2020 (COPELABS) and UIDB/05380/2020 (HEI-Lab).  ... 
doi:10.1016/j.caeai.2021.100014 fatcat:wdfufol3nne53fpwl6a2fajgce

AI Researchers, Video Games Are Your Friends! [chapter]

Julian Togelius
2016 Studies in Computational Intelligence  
The chapter is based on my keynote at IJCCI 2015, and is written in an attempt to be accessible to a broad audience.  ...  If you are a video game developer, you should look to AI for the technology that makes completely new types of games possible. This chapter lays out the case for both of these propositions.  ...  There are by now a set of best practices for how to organize such competition so as to maximize research value [53] . Thus, we advance AI through game-based competitions.  ... 
doi:10.1007/978-3-319-48506-5_1 fatcat:zpv2fuhu65aexe2fhukhjzxi7m

ColorShapeLinks: A Board Game AI Competition for Educators and Students [article]

Nuno Fachada
2020 arXiv   pre-print
The competition is based on an arbitrarily-sized version of the Simplexity board game, the motto of which, "simple to learn, complex to master", is curiously also applicable to AI agents.  ...  ColorShapeLinks is not only a competition, but both a game and a framework which educators and students can extend and use to host their own competitions.  ...  Acknowledgments This work is supported by Fundação para a Ciência e a Tecnologia under Grants UIDB/04111/2020 (COPELABS) and UIDB/05380/2020 (HEI-Lab).  ... 
arXiv:2012.09015v1 fatcat:w7v2vnajpjbkxmuwvlp6dmuis4

Evaluation of StarCraft Artificial Intelligence Competition Bots by Experienced Human Players

Man-Je Kim, Kyung-Joong Kim, SeungJun Kim, Anind K. Dey
2016 Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA '16  
AI matches without human involvement. It is questionable whether successful AI bots are also competitive and preferable to human players.  ...  Since 2010, game AI researchers have hosted annual AI competition events to develop human-level RTS AIs using StarCraft. It ranks the AI bots by their winning ratio from thousands of AI vs.  ...  Since 2010, annual RTS game AI competitions have been launched to promote the development of successful AI players [6] .  ... 
doi:10.1145/2851581.2892305 dblp:conf/chi/KimKKD16 fatcat:mf65yc6xk5dr7fkdmjbirhsqyy

Investigating vanilla MCTS scaling on the GVG-AI game corpus

Mark J. Nelson
2016 2016 IEEE Conference on Computational Intelligence and Games (CIG)  
The General Video Game AI Competition (GVG-AI) invites submissions of controllers to play games speciied in the Video Game Description Language (VGDL), testing them against each other and several baselines  ...  To better understand the potential performance of the baseline vanilla MCTS controller, I perform scaling experiments, running it against the 62 games in the public GVG-AI corpus as the time budget is  ...  Acknowledgment This work was supported in part by the European Union FP7 grant 621403 (ERA Chair: Games Research Opportunities). Thanks to the reviewers for helpful comments and suggestions.  ... 
doi:10.1109/cig.2016.7860443 dblp:conf/cig/Nelson16 fatcat:36avwpcgrrbgtgrxsz4vz4upqu

A new design for a Turing Test for Bots

Philip Hingston
2010 Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games  
To answer these questions, the author designed and organised a game bot programming competition, the BotPrize, in which competitors submit bots that try to pass a "Turing Test for Bots".  ...  In this paper, we describe a new design for the competition, which will make it simpler to run, and, we hope, open up new opportunities for innovative use of the testing platform.  ...  ACKNOWLEDGMENTS The author would like to thank 2K Marin (formerly 2K Australia) for its support for the BotPrize competition, the competitors, judges and confederates in the BotPrize competitions for taking  ... 
doi:10.1109/itw.2010.5593336 dblp:conf/cig/Hingston10 fatcat:lzdokymsxzgq7o3twqszisdlt4
« Previous Showing results 1 — 15 out of 21,266 results