Filters








165 Hits in 7.3 sec

On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCup

Martin Riedmiller, Thomas Gabel
<span title="">2007</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rhd7ssklwncwpd7fotjzyiag4e" style="color: black;">2007 IEEE Symposium on Computational Intelligence and Games</a> </i> &nbsp;
In this paper, we report on our experiences and achievements in applying Reinforcement Learning (RL) methods in the scope of our Brainstormers competition team within the Simulation League of RoboCup during  ...  While the application of machine learning techniques in this domain represents a promising idea in itself, the competitive character of RoboCup also evokes the desire to head for the development of learning  ...  The paper at hand gives an overview over approaches and experiences with Reinforcement Learning methods applied in our Brainstormers competition team within the Simulation League of RoboCup during the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2007.368074">doi:10.1109/cig.2007.368074</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cig/RiedmillerG07.html">dblp:conf/cig/RiedmillerG07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3xp2mrgi7fc5rcsnigclxovksa">fatcat:3xp2mrgi7fc5rcsnigclxovksa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170705075532/http://ml.informatik.uni-freiburg.de/_media/publications/riedmillergabel07c.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/a2/c6/a2c658aeed2aae89564a10fd4c1c9e7151b11847.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cig.2007.368074"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Survey of Opponent Modeling in Adversarial Domains

Samer Nashed, Shlomo Zilberstein
<span title="2022-01-14">2022</span> <i title="AI Access Foundation"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/4ax4efcwajcgvidb6hcg6mwx4a" style="color: black;">The Journal of Artificial Intelligence Research</a> </i> &nbsp;
Finally, we list several open problems and discuss future research directions inspired by AI research on opponent modeling and related research in other disciplines.  ...  These discussions lead us to propose a new form of analysis for describing and predicting the evolution of game states over time.  ...  We also thank the editors for their patience and guidance.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.1.12889">doi:10.1613/jair.1.12889</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o6wlyjr2gvdz3fs6b6szr6y55u">fatcat:o6wlyjr2gvdz3fs6b6szr6y55u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220421232059/https://jair.org/index.php/jair/article/download/12889/26762" 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/60/2f/602faa3d4393426fab5ec2cf0dd399f6a886700a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1613/jair.1.12889"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

On being a teammate

Stacy Marsella, Jafar Adibi, Yaser Al-Onaizan, Gal A. Kaminka, Ion Muslea, Milind Tambe
<span title="">1999</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/udh3bimsxzd53iatb4uchhwvwm" style="color: black;">Proceedings of the third annual conference on Autonomous Agents - AGENTS &#39;99</a> </i> &nbsp;
We h a ve elded two teams, ISIS97 and ISIS98, in RoboCup competitions. These teams have been in the top four teams in these competitions.  ...  Increasingly, m ulti-agent systems are being designed for a variety of complex, dynamic domains.  ...  Another skill, to intercept the ball, used a mix of o -line and on-line relied on reinforcement learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/301136.301199">doi:10.1145/301136.301199</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/agents/MarsellaAAKMT99.html">dblp:conf/agents/MarsellaAAKMT99</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sldoshu55zeihl4vpb5ba6i3fa">fatcat:sldoshu55zeihl4vpb5ba6i3fa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20090527034134/http://www.isi.edu/~muslea/PS/99-agents.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/9e/e0/9ee07afda8a026b70b8b3abefdabd2c9713e5004.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/301136.301199"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Representation and Learning Methods for Situation Evaluation in RoboCup Soccer Simulation

Hidehisa AKIYAMA, Tomoharu NAKASHIMA, Harukazu IGARASHI
<span title="2020-04-15">2020</span> <i title="Japan Society for Fuzzy Theory and Intelligent Informatics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qiqxgjydfvdtraxj47xwpnmo4a" style="color: black;">Journal of Japan Society for Fuzzy Theory and Intelligent Informatics</a> </i> &nbsp;
Gabel: "On Experiences in a Complex and Competitive Gaming Domain: Reinforcement Learning Meets RoboCup," Proc. of the 2007 IEEE Symposium on Computational Intelligence and Games, pp. 17-23, 2007.  ...  Stone: "Half Field Offence in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study," RoboCup-2006: Robot Soccer World Cup X, pp. 72-85, Springer-Verlag, 2007.  ...  Abstract: In this paper, representations of a situation evaluation model and their learning methods in RoboCup soccer simulation 2D are reviewed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3156/jsoft.32.2_691">doi:10.3156/jsoft.32.2_691</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5lt44twwhbdeng57bfcn4dftoi">fatcat:5lt44twwhbdeng57bfcn4dftoi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505072545/https://www.jstage.jst.go.jp/article/jsoft/32/2/32_691/_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/97/72/9772cd418819332ccbe62ac217fcc5363ba65a02.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3156/jsoft.32.2_691"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Building agent teams using an explicit teamwork model and learning

Milind Tambe, Jafar Adibi, Yaser Al-Onaizan, Ali Erdem, Gal A. Kaminka, Stacy C. Marsella, Ion Muslea
<span title="">1999</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/weoplee4x5anpi62cco5v4higa" style="color: black;">Artificial Intelligence</a> </i> &nbsp;
W e also demonstrate the application of o -line and on-line learning to improve and specialize agents' individual skills in RoboCup.  ...  Multi-agent collaboration or teamwork and learning are two critical research c hallenges in a large number of multi-agent applications.  ...  We also thank Peter Stone and Manuela Veloso for providing us player-agents of CMUnited, which provided a good opponent team to practice against in the weeks leading up to RoboCup'97.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0004-3702(99)00022-3">doi:10.1016/s0004-3702(99)00022-3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3imbg7myfnfqvdqyilrgfdsf6a">fatcat:3imbg7myfnfqvdqyilrgfdsf6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20051129112541/http://www.isi.edu:80/~muslea/PS/99-aij-robocup.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/62/6f/626f3c5d6862f3b0c376e742f332cbb2c94069a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0004-3702(99)00022-3"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

RoboCup: Today and tomorrow—What we have learned

Minoru Asada, Hiroaki Kitano, Itsuki Noda, Manuela Veloso
<span title="">1999</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/weoplee4x5anpi62cco5v4higa" style="color: black;">Artificial Intelligence</a> </i> &nbsp;
First, the issue on what and why RoboCup is addressed, and a wide range of research issues are explained.  ...  This article describes what we have learned from the past RoboCup activities, mainly the first and the second RoboCups, and overviews the future perspectives of RoboCup in the next century.  ...  Acknowledgement Initial inputs to this article from Milind Tambe (ISI-USC, USA) and Gerhard K. Kraetzschmar (University of Ulm, Germany) are appreciated.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0004-3702(99)00024-7">doi:10.1016/s0004-3702(99)00024-7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/noiwpb42bbh6nnbcceisvzre74">fatcat:noiwpb42bbh6nnbcceisvzre74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171002183301/http://publisher-connector.core.ac.uk/resourcesync/data/elsevier/pdf/bc3/aHR0cDovL2FwaS5lbHNldmllci5jb20vY29udGVudC9hcnRpY2xlL3BpaS9zMDAwNDM3MDI5OTAwMDI0Nw%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/7c/19/7c19aca0ab38ca8fb4362143741ea68473c4ce7d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0004-3702(99)00024-7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Disruptive innovations in RoboCup 2D Soccer Simulation League: from Cyberoos'98 to Gliders2016 [article]

Mikhail Prokopenko, Peter Wang
<span title="2016-12-03">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A common feature is that different champion teams succeeded in finding a way to decompose the enormous search-space of possible single- and multi-agent behaviours, by automating the exploration of the  ...  We review disruptive innovations introduced in the RoboCup 2D Soccer Simulation League over the twenty years since its inception, and trace the progress of our champion team (Gliders).  ...  We thank David Budden for developing a new self-localisation method introduced in Gliders2013 [49, 34] as well as contributing to the analysis of competition formats [4] , and Oliver Cliff for developing  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.00947v1">arXiv:1612.00947v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yke3drnyn5arhlc3ppkrs6xan4">fatcat:yke3drnyn5arhlc3ppkrs6xan4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200928040317/https://arxiv.org/pdf/1612.00947v1.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/c9/83/c9832e5c4774554d39dff91336ef28f7f9b0ae91.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1612.00947v1" 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>

RoboCup as an Introduction to CS Research [chapter]

Peter Stone
<span title="">2004</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
Experiences are presented from the design and implementation of such a course.  ...  The course is structured around an ongoing incremental programming project that culminates in a class tournament in the RoboCup Soccer Server, an open-source infrastructure built to support multiagent  ...  The author also wishes to thank Vinay Sampath Kumar, a TA for the 2002 version of the course, as well as the NYU and UT Austin students who have participated in the course.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-25940-4_25">doi:10.1007/978-3-540-25940-4_25</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pmsh3bhio5dwrntyngvvyq277m">fatcat:pmsh3bhio5dwrntyngvvyq277m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120302104256/http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/LNAI2003-class.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/f3/7c/f37c9ef05c62dc43c40cd685b6996c842ac0996a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-540-25940-4_25"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

RoboCup-2003: New Scientific and Technical Advances

Enrico Pagello, Emanuele Menegatti, Ansgar Bredenfeld, Paulo Costa, Thomas Christaller, Adam Jacoff, Daniel Polani, Martin A. Riedmiller, Alessandro Saffiotti, Elizabeth Sklar, Takashi Tomoichi
<span title="">2004</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/27wksbinzzhjfow2wuy6m2iefm" style="color: black;">The AI Magazine</a> </i> &nbsp;
focused on education), and (4) a Scientific Symposium.  ...  In this article, in addition to reporting on the results of the games, we highlight the robotics and AI technologies exploited by the teams in the different leagues and describe the most meaningful scientific  ...  Acknowledgments We want to thank all the people who contributed to the writing of this article, in particular, Jeffrey Johnson, Brett Browning,  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aimag.v25i2.1762">doi:10.1609/aimag.v25i2.1762</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/journals/aim/PagelloMBCCJPRSST04.html">dblp:journals/aim/PagelloMBCCJPRSST04</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cptqliviezdhhlyzzofa75taci">fatcat:cptqliviezdhhlyzzofa75taci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20151019082157/http://www.aaai.org/ojs/index.php/aimagazine/article/download/1762/1660" 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/9f/75/9f7566262516d8a344fc52148ddbcdcac2e58b96.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aimag.v25i2.1762"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Action-selection in RoboCup Keepaway Soccer: Experimenting with Player Confidence

Samara Neilson
<span title="2013-09-05">2013</span> <i title="Figshare"> Figshare </i> &nbsp;
, Reinforcement Learning, Q-Learning and Potential Fields.  ...  In order to address these issues, a meaningful method of on-field player evaluation, the confidence model, was first proposed then implemented as an action-selection policy.  ...  And, finally, I am forever indebted to my friends and family for their understanding, endless patience, encouragement and support when it was most required.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6084/m9.figshare.789063">doi:10.6084/m9.figshare.789063</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hvhcow3enbe2xdqqd4rbl6yki4">fatcat:hvhcow3enbe2xdqqd4rbl6yki4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200113075728/https://s3-eu-west-1.amazonaws.com/pfigshare-u-files/1191318/SANeilsonMastersThesis.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/94/86/9486b9e59a3efe7ba202712a9368a021bdba262f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6084/m9.figshare.789063"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> figshare.com </button> </a>

The robocup physical agent challenge: Phase i

Minoru Asada, Peter Stone, Hiroaki Kitano, Barry Werger, Yasuo Kuniyoshi, Alexis Drogoul, Dominique Duhaut, Manuela Veloso, Hajime Asama, Sho'Ji Suzuki
<span title="">1998</span> <i title="Informa UK Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pcyo5wihbzcwxb7m76lyrd4tvu" style="color: black;">Applied Artificial Intelligence</a> </i> &nbsp;
In order for the robots to play a soccer game reasonably well, a wide range of technologies needs to be integrated and a number of technical breakthroughs must be made.  ...  The RoboCup Physical Agent Challenge provides a good testbed for studying how p h ysical bodies play a signi cant role in realizing intelligent behaviors using the RoboCup framework Kitano, et al., 9 5  ...  These skills are needed to realize cooperative behaviors with teammates and competitive ones against opponents in soccer game.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/088395198117857">doi:10.1080/088395198117857</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xcory33ganboxcukmczr6cwyrm">fatcat:xcory33ganboxcukmczr6cwyrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810123321/http://www.cs.utexas.edu/~pstone/Papers/bib2html-links/hardware-challenge97.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/6d/26/6d2687fc7941fcc70d35a2b58ebf6a74914e9f39.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1080/088395198117857"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> tandfonline.com </button> </a>

Cooperative Multi-Agent Learning: The State of the Art

Liviu Panait, Sean Luke
<span title="">2005</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7rdrzlhoxjb5ho2u76erh6zpni" style="color: black;">Autonomous Agents and Multi-Agent Systems</a> </i> &nbsp;
In this survey we attempt to draw from multi-agent learning work in a spectrum of areas, including reinforcement learning, evolutionary computation, game theory, complex systems, agent modeling, and robotics  ...  Reinforcement Learning Reinforcement learning (RL) methods are particularly useful in domains where reinforcement 2 information (expressed as penalties or rewards) is provided after a sequence of actions  ...  Bowling and Veloso [26] examine a number of game theory and reinforcement learning approaches to stochastic games, and describe the differences in the assumptions they make.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-005-2631-2">doi:10.1007/s10458-005-2631-2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u3xlftotajfitdtfmvbmggwgbi">fatcat:u3xlftotajfitdtfmvbmggwgbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060907114829/http://mas.cs.umass.edu/classes/cs691V/papers/panait05cmasl.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/a1/bf/a1bfaebbc688eae8bfafae812aaebab65513a788.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-005-2631-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

RoboCup: 10 Years of Achievements and Future Challenges

Ubbo Visser, Hans-Dieter Burkhard
<span title="">2007</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/27wksbinzzhjfow2wuy6m2iefm" style="color: black;">The AI Magazine</a> </i> &nbsp;
RoboCup is also about the nature of intelligence, and playing soccer acts as a performance measure of systems that contain artificial intelligence-in much the same way chess has been used over the last  ...  There are serious research questions that have to be tackled behind the scenes of a soccer game: perception, decision making, action selection, hardware design, materials, energy, and more.  ...  The results were compiled by the organizing committee members of RoboCup 2006 and in particular by Sven Behnke, Andreas Birk, Joschka Boedecker, Carlos Cardeira, Alexander Kleiner, Tim Laue, Paul Plöger  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aimag.v28i2.2044">doi:10.1609/aimag.v28i2.2044</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/journals/aim/VisserB07.html">dblp:journals/aim/VisserB07</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pamc2sytwzfidk3axiil5l5yni">fatcat:pamc2sytwzfidk3axiil5l5yni</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20151020000313/http://www.aaai.org/ojs/index.php/aimagazine/article/download/2044/1937" 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/3e/10/3e102d418e4f3186d077b4b873e64b473864bde5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aimag.v28i2.2044"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Online Planning for Large Markov Decision Processes with Hierarchical Decomposition

Aijun Bai, Feng Wu, Xiaoping Chen
<span title="2015-07-15">2015</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gmnsxns6fvf23c44lkzaej5laq" style="color: black;">ACM Transactions on Intelligent Systems and Technology</a> </i> &nbsp;
We have also conducted a long-term case study in a highly-complex simulated soccer domain and developed a team named WrightEagle that has won 5 world champions and 5 runners-up in the recent 10 years of  ...  In the context of reinforcement learning, MAXQ is a value function decomposition method that exploits the underlying structure of the original MDP and decomposes it into a combination of smaller subproblems  ...  [2005] have done a lot of work on applying reinforcement learning methods to RoboCup 2D.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2717316">doi:10.1145/2717316</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/x55oirne65ewhdruxyqu5maxmq">fatcat:x55oirne65ewhdruxyqu5maxmq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150702001858/http://tist.acm.org:80/papers/ACM-TIST-V6N4-TIST-2014-04-0115.R1.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/d0/dc/d0dc8eb49b272acafa2e1cf8de391cdfb186aa99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2717316"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Reinforcement Learning for RoboCup Soccer Keepaway

Peter Stone, Richard S. Sutton, Gregory Kuhlmann
<span title="">2005</span> <i title="SAGE Publications"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gofyg7sszvgrhklhtsvngvyobu" style="color: black;">Adaptive Behavior</a> </i> &nbsp;
RoboCup simulated soccer presents many challenges to reinforcement learning methods, including a large state space, hidden and uncertain state, multiple independent agents learning simultaneously, and  ...  We describe our application of episodic SMDP Sarsa(λ) with linear tile-coding function approximation and variable λ to learning higher-level decisions in a keepaway subtask of RoboCup soccer.  ...  Acknowledgments We thank Satinder Singh for his assistance in formulating our reinforcement learning approach to keepaway; Patrick Riley and Manuela Veloso for their participation in the creation of the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1177/105971230501300301">doi:10.1177/105971230501300301</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eafbfedppnbg3pcrjhmgotktvq">fatcat:eafbfedppnbg3pcrjhmgotktvq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170810025948/http://papersdb.cs.ualberta.ca/~papersdb/uploaded_files/460/paper_AB05.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/50/52/5052f508d4acbcbefa539522d98d9bf341602498.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1177/105971230501300301"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> sagepub.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 165 results