Filters








80,399 Hits in 3.0 sec

On Learning From Game Annotations

Christian Wirth, Johannes Furnkranz
<span title="">2015</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
We extract preferences from large-scale database for annotated chess games and use them for calculating the feature weights of a heuristic chess position evaluation function.  ...  Most of the research in the area of evaluation function learning is focused on self-play. However in many domains, like chess, expert feedback is amply available in the form of annotated games.  ...  In a last step, action preferences (s, a1 a2) are converted to state preferences by applying a1 and a2 to s, resulting in state preferences s1 s2, where si = MOVE(s, ai).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2332442">doi:10.1109/tciaig.2014.2332442</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sh5tti6jlred5cf4g6zjmh5y3u">fatcat:sh5tti6jlred5cf4g6zjmh5y3u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170705123758/http://www.ke.tu-darmstadt.de/events/PL-12/papers/11-wirth.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f6/04/f604a38192b359afc8881dbfeff94bd678819521.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2332442"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

1GBDT, LR & Deep Learning for Turn-based Strategy Game AI

Like Zhang, Hui Pan, Qi Fan, Changqing Ai, Yanqing Jing
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rhd7ssklwncwpd7fotjzyiag4e" style="color: black;">2019 IEEE Conference on Games (CoG)</a> </i> &nbsp;
Finally, we productionized and evaluated the system on SA 2, a commercial mobile turn-based game.  ...  This paper proposes an AI fighting strategies generation approach implemented in the turn-based fighting game StoneAge 2 (SA2).  ...  Acknowledgements We would like to thank many at Shanghai Luyou Network Technology, especially Dian Wu, Jun Qi for the robot script, and early feedback on the GLD model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2019.8848103">doi:10.1109/cig.2019.8848103</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cig/ZhangPFAJ19.html">dblp:conf/cig/ZhangPFAJ19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sd3i4gvnmngvfdmbxqhzcbn3pq">fatcat:sd3i4gvnmngvfdmbxqhzcbn3pq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319200155/https://easychair.org/publications/preprint_open/QCWC" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7d/9a/7d9a0b3f6b847d7d6ef4183d38d2ae216892e91d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2019.8848103"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Grammars for Games: A Gradient-Based, Game-Theoretic Framework for Optimization in Deep Learning

David Balduzzi
<span title="2016-01-18">2016</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/t4zwwbshrrfd3hjbg4s3bysm7q" style="color: black;">Frontiers in Robotics and AI</a> </i> &nbsp;
The main ingredients of the framework are, thus, unsurprisingly: (i) game theory, to formalize distributed optimization; and (ii) communication protocols, to track the flow of zeroth and first-order information  ...  Deep learning is currently the subject of intensive study.  ...  Frontiers in Robotics and AI | www.frontiersin.org January 2016 | Volume 2 | Article 39 Frontiers in Robotics and AI | www.frontiersin.org January 2016 | Volume 2 | Article 39 Nature's outputs  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frobt.2015.00039">doi:10.3389/frobt.2015.00039</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/re4eibywmbb7xkcxti47coi5te">fatcat:re4eibywmbb7xkcxti47coi5te</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171007132636/http://publisher-connector.core.ac.uk/resourcesync/data/Frontiers/pdf/b83/aHR0cDovL2pvdXJuYWwuZnJvbnRpZXJzaW4ub3JnL2FydGljbGUvMTAuMzM4OS9mcm9idC4yMDE1LjAwMDM5L3BkZg%3D%3D.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8a/03/8a03ccecf9b6aec006b41edf64c57a12e5239e1a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frobt.2015.00039"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a>

Reinforcement Learning in First Person Shooter Games

Michelle McPartland, Marcus Gallagher
<span title="">2011</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
Index Terms-Artificial intelligence (AI), computer games, reinforcement learning (RL).  ...  Reinforcement learning (RL) is a popular machine learning technique that has many successes in learning how to play classic style games.  ...  Predictability can be overcome by allowing a small learning rate during the game, allowing the AIs to slowly adapt to their surroundings.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2010.2100395">doi:10.1109/tciaig.2010.2100395</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6wokbhm6rjhpnklvep3zutd7vi">fatcat:6wokbhm6rjhpnklvep3zutd7vi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160304184218/http://staff.itee.uq.edu.au/marcusg/papers/mcpartland_gallagher_tr_ciaig.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d1/56/d15646e65dddb8616661c4a928485c745a1323d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2010.2100395"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning [article]

Inseok Oh, Seungeun Rho, Sangbin Moon, Seongho Son, Hyoil Lee, and Jinyun Chung
<span title="2020-01-31">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We overcame these challenges and made 1v1 battle AI agents for the commercial game "Blade & Soul". The trained agents competed against five professional gamers and achieved a win rate of 62%.  ...  Reinforcement learning combined with deep neural networks has performed remarkably well in many genres of games recently.  ...  We created pro-level AI agents for the real-time fighting game "Blade & Soul (B&S) Arena Battle" via novel self-play based reinforcement learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.03821v3">arXiv:1904.03821v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qfr7n2t6kzandaem2bqwas47wa">fatcat:qfr7n2t6kzandaem2bqwas47wa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200811085949/https://arxiv.org/ftp/arxiv/papers/1904/1904.03821.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.03821v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Game AI: Simulating Car Racing Game by Applying Pathfinding Algorithms

Jung-Ying Wang, Yong-Bin Lin
<span title="">2012</span> <i title="EJournal Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2uckwik5xjerdg36acn26gjq6e" style="color: black;">International Journal of Machine Learning and Computing</a> </i> &nbsp;
Three real speedways of Formula one (F1) are selected as our game speedways, to simulate and analyze our study.  ...  In this paper, two modified A* algorithms to effectively solve the pathfinding problem in a static obstacles racing game are proposed.  ...  A heuristic function is used to create this estimate on how far Game AI: Simulating Car Racing Game by Applying Pathfinding Algorithms Jung-Ying Wang and Yong-Bin Lin away it will take to reach the goal  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7763/ijmlc.2012.v2.82">doi:10.7763/ijmlc.2012.v2.82</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/inmzeelojfen3e64yg5wsusoba">fatcat:inmzeelojfen3e64yg5wsusoba</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819093238/http://www.ijmlc.org:80/papers/82-A1090.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/03/a0/03a00a000b25239c0c08d1138326fcd468e9b17d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7763/ijmlc.2012.v2.82"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Authenticity, Interactivity, and Collaboration in VR Learning Games

Meredith M. Thompson, Annie Wang, Dan Roy, Eric Klopfer
<span title="2018-12-19">2018</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/t4zwwbshrrfd3hjbg4s3bysm7q" style="color: black;">Frontiers in Robotics and AI</a> </i> &nbsp;
We share our perspectives on the benefits and challenges of applying these principles in a learning game about cellular biology.  ...  We propose the theoretical framework of embodied learning and discuss how VR and reflect on current research findings to outline effective applications of VR and provide guidelines in developing educational  ...  Our labs have developed a number of learning simulations and games, and are currently developing a game to introduce students to cellular biology.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frobt.2018.00133">doi:10.3389/frobt.2018.00133</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33501011">pmid:33501011</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7805727/">pmcid:PMC7805727</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uzdyhh7fynbr3ceho3egybf3ku">fatcat:uzdyhh7fynbr3ceho3egybf3ku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190303005852/http://pdfs.semanticscholar.org/bfb3/dac742c6c98c5460b0617b76f6305d24c19a.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bf/b3/bfb3dac742c6c98c5460b0617b76f6305d24c19a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frobt.2018.00133"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805727" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Online Adaptable Learning Rates for the Game Connect-4

Samineh Bagheri, Markus Thill, Patrick Koch, Wolfgang Konen
<span title="">2016</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
But in order to be successful with temporal difference learning on game tasks, often a careful selection of features and a large number of training games is necessary.  ...  Learning board games by self-play has a long tradition in computational intelligence for games.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their helpful comments and for pointing out important adaptive learning references.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2367105">doi:10.1109/tciaig.2014.2367105</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zgd4qmasxfanloehaqek2pdohe">fatcat:zgd4qmasxfanloehaqek2pdohe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809061209/http://www.gm.fh-koeln.de/~konen/Publikationen/Bagh15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6a/3c/6a3caf5cfabdc7cf924c32efe1cefe941ce98b62.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2367105"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning-Based Procedural Content Generation

Jonathan Roberts, Ke Chen
<span title="">2015</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
Procedural content generation (PCG) has recently become one of the hottest topics in computational intelligence and AI game research.  ...  By exploring and exploiting information gained in game development and public player test, our framework can generate robust content adaptable to end-user or target players on-line with minimal interruption  ...  Also the authors are grateful to all anonymous public players for their feedback in the public survey and all the target players who participated in our simulation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2335273">doi:10.1109/tciaig.2014.2335273</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r2pbhpycdjejbemgcvji5zs7qy">fatcat:r2pbhpycdjejbemgcvji5zs7qy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170705092432/http://staff.cs.manchester.ac.uk/%7Ekechen/publication/tciaig2015.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/96/59966dfd5eac2ee3c9d50e259e481b73caaaa710.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2014.2335273"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Combining Reinforcement Learning with a Multi-level Abstraction Method to Design a Powerful Game AI

Charles Madeira, Vincent Corruble
<span title="">2011</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6dp3dzlqc5gkhercrq23224pl4" style="color: black;">2011 Brazilian Symposium on Games and Digital Entertainment</a> </i> &nbsp;
We also study specifically various reward signals as well as interagent communication setups and show their impact on the Game AI performance, distinctively in offensive and defensive modes.  ...  This paper investigates the design of a challenging Game AI for a modern strategy game, which can be seen as a large-scale multiagent simulation of an historical military confrontation.  ...  As a result, a distributed approach to the design of a Game AI for this type of game is a natural and reasonable candidate to be explored.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/sbgames.2011.21">doi:10.1109/sbgames.2011.21</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sbgames/MadeiraC11.html">dblp:conf/sbgames/MadeiraC11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ebj737eodvaslmgkzsdsil6hea">fatcat:ebj737eodvaslmgkzsdsil6hea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808161245/http://www.sbgames.org/sbgames2011/proceedings/sbgames/papers/comp/full/15-92238_2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/87/91/8791f3beabd0f00f66903f73a2d42ede38fd0787.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/sbgames.2011.21"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Applying Reinforcement Learning for Game AI in a Tank-Battle Game

Yung-Ping Fang, I-Hsien Ting
<span title="">2009</span> <i title="IEEE"> 2009 Fourth International Conference on Innovative Computing, Information and Control (ICICIC) </i> &nbsp;
In this paper, we try to build a Tank-battle computer game and use the methodology of reinforcement learning for the NPCs (the tanks).  ...  In the research field of game AIs, it is a good approach that can give the nonplayer-characters (NPCs) in digital games more human-like qualities.  ...  In Section 2, the related works and literature regarding reinforcement learning and game AI will be reviewed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icicic.2009.114">doi:10.1109/icicic.2009.114</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6mxut3kupbhepophe45bnw3xm4">fatcat:6mxut3kupbhepophe45bnw3xm4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320011921/http://www.jsoftware.us/vol5/jsw0512-3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3f/51/3f51839c5f78f075c16155d0b9850ff9b32b2dfd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icicic.2009.114"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Creating large numbers of game AIs by learning behavior for cooperating units

Stephen Wiens, Jorg Denzinger, Sanjeev Paskaradevan
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rhd7ssklwncwpd7fotjzyiag4e" style="color: black;">2013 IEEE Conference on Computational Inteligence in Games (CIG)</a> </i> &nbsp;
We present two improvements to the hybrid learning method for the shout-ahead architecture for units in the game Battle for Wesnoth.  ...  Our improvements add knowledge about terrain to the learning and also evaluate unit behaviors on several scenario maps to learn more general rules.  ...  and consequently game AIs of various difficulty out of a single human developed game AI.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2013.6633608">doi:10.1109/cig.2013.6633608</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cig/WiensDP13.html">dblp:conf/cig/WiensDP13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/63crvwqda5fw3g5pjcnp2da2sy">fatcat:63crvwqda5fw3g5pjcnp2da2sy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140602182404/http://eldar.mathstat.uoguelph.ca:80/dashlock/CIG2013/papers/paper_1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3d/af/3daf6886fcff66dff38f7caa38d221cce000824d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2013.6633608"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation [article]

Kun Wang, WaiChing Sun, Qiang Du
<span title="2019-03-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We introduce a multi-agent meta-modeling game to generate data, knowledge, and models that make predictions on constitutive responses of elasto-plastic materials.  ...  uses reinforcement learning to design new experiments to optimize the prediction capacity.  ...  Following this, we will introduce the detailed design of the data collection/metamodeling game for modeling the collaboration of the AI data agent and the AI modeler agent (Section 3).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.04307v1">arXiv:1903.04307v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iluknt5mzvdrhotw4yrlmlatnm">fatcat:iluknt5mzvdrhotw4yrlmlatnm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903224327/https://arxiv.org/pdf/1903.04307v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1b/d9/1bd939ebb432ea42910b0c001876cac69bc1f785.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1903.04307v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Relationship Between Generalization and Diversity in Coevolutionary Learning

Siang Yew Chong, P. Tino, Xin Yao
<span title="">2009</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
Games have long played an important role in the development and understanding of coevolutionary learning systems.  ...  We study two important issues in coevolutionary learning-generalization performance and diversity-using games.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous associate editor and reviewers for their comments that have helped to improve this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2009.2034269">doi:10.1109/tciaig.2009.2034269</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/loqpbdo76zarxm6mvpr6wbc6n4">fatcat:loqpbdo76zarxm6mvpr6wbc6n4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110401063735/http://www.cs.bham.ac.uk/~xin/papers/ChongTinoYaoTCIAIG09.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d7/04/d704d6b9796451b1e3db55c0737e343114844a55.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2009.2034269"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning Finite-State Machine Controllers From Motion Capture Data

M. Gillies
<span title="">2009</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e3irxgosbfdlvgbpxbgqltq3va" style="color: black;">IEEE Transactions on Computational Intelligence and AI in Games</a> </i> &nbsp;
With characters in computer games and interactive media increasingly being based on real actors, the individuality of an actor's performance should not only be reflected in the appearance and animation  ...  The method learns both the transition probabilities of the Finite State Machine and also how to select animations based on the current state. * M. Gillies is with the  ...  The author would like to thank the member of the UCL Department of Computing Virtual Environments and Computer Graphics group and the UCL Centre for Computational Statistics and Machine Learning for their  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2009.2019630">doi:10.1109/tciaig.2009.2019630</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dduinsn65zhlxk27rlusio7nj4">fatcat:dduinsn65zhlxk27rlusio7nj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160715082418/http://research.gold.ac.uk/2290/1/fsm_preprint.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a5/24/a524ba391036c461596edf02eff5e03d55def473.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tciaig.2009.2019630"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 80,399 results