Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Kazuteru Miyazaki
@article{DBLP:journals/access/KodamaHM22,
author = {Naoki Kodama and
Taku Harada and
Kazuteru Miyazaki},
title = {Traffic Signal Control System Using Deep Reinforcement Learning With
Emphasis on Reinforcing Successful Experiences},
journal = {{IEEE} Access},
volume = {10},
pages = {128943--128950},
year = {2022},
url = {https://doi.org/10.1109/ACCESS.2022.3225431},
doi = {10.1109/ACCESS.2022.3225431},
timestamp = {Thu, 05 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/access/KodamaHM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bica/Miyazaki22,
author = {Kazuteru Miyazaki},
editor = {F{\'{e}}lix F. Ramos Corchado and
Alexei V. Samsonovich},
title = {Modeling of placebo effect in stochastic reward tasks by reinforcement
learning},
booktitle = {Proceedings of the 2022 Annual International Conference on Brain-Inspired
Cognitive Architectures for Artificial Intelligence, BICA*AI 2022,
13th Annual Meeting of the {BICA} Society, September 22-24, 2022,
Guadalajara, Mexico},
series = {Procedia Computer Science},
volume = {213},
pages = {255--262},
publisher = {Elsevier},
year = {2022},
url = {https://doi.org/10.1016/j.procs.2022.11.064},
doi = {10.1016/J.PROCS.2022.11.064},
timestamp = {Wed, 25 Jan 2023 14:01:03 +0100},
biburl = {https://dblp.org/rec/conf/bica/Miyazaki22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/access/KodamaHM21,
author = {Naoki Kodama and
Taku Harada and
Kazuteru Miyazaki},
title = {Home Energy Management Algorithm Based on Deep Reinforcement Learning
Using Multistep Prediction},
journal = {{IEEE} Access},
volume = {9},
pages = {153108--153115},
year = {2021},
url = {https://doi.org/10.1109/ACCESS.2021.3126365},
doi = {10.1109/ACCESS.2021.3126365},
timestamp = {Wed, 15 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/access/KodamaHM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/cogsr/Miyazaki21,
author = {Kazuteru Miyazaki},
title = {Proposal and evaluation of deep exploitation-oriented learning under
multiple reward environment},
journal = {Cogn. Syst. Res.},
volume = {70},
pages = {29--39},
year = {2021},
url = {https://doi.org/10.1016/j.cogsys.2021.07.002},
doi = {10.1016/J.COGSYS.2021.07.002},
timestamp = {Wed, 03 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/cogsr/Miyazaki21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bica/Miyazaki20,
author = {Kazuteru Miyazaki},
editor = {Alexei V. Samsonovich and
Valentin V. Klimov},
title = {Application of Deep Reinforcement Learning to Decision-Making System
based on Consciousness},
booktitle = {Proceedings of the 2020 Annual International Conference on Brain-Inspired
Cognitive Architectures for Artificial Intelligence, {BICA} 2020,
Eleventh Annual Meeting of the {BICA} Society, November 10-15, 2020,
Virtual Event / Natal, Rio Grande do Norte, Brazil},
series = {Procedia Computer Science},
volume = {190},
pages = {631--636},
publisher = {Elsevier},
year = {2020},
url = {https://doi.org/10.1016/j.procs.2021.06.074},
doi = {10.1016/J.PROCS.2021.06.074},
timestamp = {Thu, 10 Nov 2022 12:41:19 +0100},
biburl = {https://dblp.org/rec/conf/bica/Miyazaki20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iciss2/Miyazaki20,
author = {Kazuteru Miyazaki},
title = {Classification of Medical Data using Character-level {CNN}},
booktitle = {{ICISS} 2020: The 3rd International Conference on Information Science
and System, Cambridge, UK, March 19-22, 2020},
pages = {43--47},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3388176.3388191},
doi = {10.1145/3388176.3388191},
timestamp = {Fri, 07 Aug 2020 15:43:48 +0200},
biburl = {https://dblp.org/rec/conf/iciss2/Miyazaki20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/KodamaHM19,
author = {Naoki Kodama and
Taku Harada and
Kazuteru Miyazaki},
title = {Deep Reinforcement Learning with Dual Targeting Algorithm},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2019 Budapest,
Hungary, July 14-19, 2019},
pages = {1--6},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/IJCNN.2019.8851690},
doi = {10.1109/IJCNN.2019.8851690},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/KodamaHM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmla/KodamaMH18,
author = {Naoki Kodama and
Kazuteru Miyazaki and
Taku Harada},
editor = {M. Arif Wani and
Mehmed M. Kantardzic and
Moamar Sayed Mouchaweh and
Jo{\~{a}}o Gama and
Edwin Lughofer},
title = {A Proposal for Reducing the Number of Trial-and-Error Searches for
Deep Q-Networks Combined with Exploitation-Oriented Learning},
booktitle = {17th {IEEE} International Conference on Machine Learning and Applications,
{ICMLA} 2018, Orlando, FL, USA, December 17-20, 2018},
pages = {983--988},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICMLA.2018.00160},
doi = {10.1109/ICMLA.2018.00160},
timestamp = {Mon, 30 Nov 2020 08:47:24 +0100},
biburl = {https://dblp.org/rec/conf/icmla/KodamaMH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/intellisys/MiyazakiKK18,
author = {Kazuteru Miyazaki and
Naoki Kodama and
Hiroaki Kobayashi},
editor = {Kohei Arai and
Supriya Kapoor and
Rahul Bhatia},
title = {Proposal and Evaluation of an Indirect Reward Assignment Method for
Reinforcement Learning by Profit Sharing Method},
booktitle = {Intelligent Systems and Applications - Proceedings of the 2018 Intelligent
Systems Conference, IntelliSys 2018, London, UK, September 6-7, 2018,
Volume 1},
series = {Advances in Intelligent Systems and Computing},
volume = {868},
pages = {187--200},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-030-01054-6\_13},
doi = {10.1007/978-3-030-01054-6\_13},
timestamp = {Mon, 18 Feb 2019 09:18:28 +0100},
biburl = {https://dblp.org/rec/conf/intellisys/MiyazakiKK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/prima/ShiraishiMK18,
author = {Daisuke Shiraishi and
Kazuteru Miyazaki and
Hiroaki Kobayashi},
editor = {Tim Miller and
Nir Oren and
Yuko Sakurai and
Itsuki Noda and
Bastin Tony Roy Savarimuthu and
Tran Cao Son},
title = {Proposal of Detour Path Suppression Method in {PS} Reinforcement Learning
and Its Application to Altruistic Multi-agent Environment},
booktitle = {{PRIMA} 2018: Principles and Practice of Multi-Agent Systems - 21st
International Conference, Tokyo, Japan, October 29 - November 2, 2018,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {11224},
pages = {638--645},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-030-03098-8\_51},
doi = {10.1007/978-3-030-03098-8\_51},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/prima/ShiraishiMK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/scisisis/MiyazakiI18,
author = {Kazuteru Miyazaki and
Masaaki Ida},
title = {Consistency Assessment between Diploma Policy and Curriculum Policy
using Character-Level {CNN}},
booktitle = {2018 Joint 10th International Conference on Soft Computing and Intelligent
Systems {(SCIS)} and 19th International Symposium on Advanced Intelligent
Systems (ISIS), Toyama, Japan, December 5-8, 2018},
pages = {626--631},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SCIS-ISIS.2018.00106},
doi = {10.1109/SCIS-ISIS.2018.00106},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/scisisis/MiyazakiI18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/TakadamaM17,
author = {Keiki Takadama and
Kazuteru Miyazaki},
title = {Editorial: Cutting Edge of Reinforcement Learning and its Hybrid Methods},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {21},
number = {5},
pages = {833},
year = {2017},
url = {https://doi.org/10.20965/jaciii.2017.p0833},
doi = {10.20965/JACIII.2017.P0833},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/TakadamaM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/Miyazaki17,
author = {Kazuteru Miyazaki},
title = {Exploitation-Oriented Learning with Deep Learning - Introducing Profit
Sharing to a Deep Q-Network -},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {21},
number = {5},
pages = {849--855},
year = {2017},
url = {https://doi.org/10.20965/jaciii.2017.p0849},
doi = {10.20965/JACIII.2017.P0849},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/Miyazaki17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/MiyazakiFK17,
author = {Kazuteru Miyazaki and
Koudai Furukawa and
Hiroaki Kobayashi},
title = {Proposal of PSwithEFP and its Evaluation in Multi-Agent Reinforcement
Learning},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {21},
number = {5},
pages = {930--938},
year = {2017},
url = {https://doi.org/10.20965/jaciii.2017.p0930},
doi = {10.20965/JACIII.2017.P0930},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/MiyazakiFK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bica/Miyazaki17,
author = {Kazuteru Miyazaki},
editor = {Alexei V. Samsonovich and
Valentin V. Klimov},
title = {Proposal of a Deep Q-network with Profit Sharing},
booktitle = {8th Annual International Conference on Biologically Inspired Cognitive
Architectures, {BICA} 2017, August 1-6, 2017, Moscow, Russia},
series = {Procedia Computer Science},
volume = {123},
pages = {302--307},
publisher = {Elsevier},
year = {2017},
url = {https://doi.org/10.1016/j.procs.2018.01.047},
doi = {10.1016/J.PROCS.2018.01.047},
timestamp = {Tue, 17 May 2022 16:11:27 +0200},
biburl = {https://dblp.org/rec/conf/bica/Miyazaki17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bica/Miyazaki16,
author = {Kazuteru Miyazaki},
editor = {Alexei V. Samsonovich and
Valentin V. Klimov},
title = {A Study of an Indirect Reward on Multi-agent Environments},
booktitle = {7th Annual International Conference on Biologically Inspired Cognitive
Architectures, {BICA} 2016, July 16-19, 2016, New York City, NY, {USA}},
series = {Procedia Computer Science},
volume = {88},
pages = {94--101},
publisher = {Elsevier},
year = {2016},
url = {https://doi.org/10.1016/j.procs.2016.07.411},
doi = {10.1016/J.PROCS.2016.07.411},
timestamp = {Tue, 17 May 2022 16:11:27 +0200},
biburl = {https://dblp.org/rec/conf/bica/Miyazaki16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eumas/MiyazakiFK16,
author = {Kazuteru Miyazaki and
Koudai Furukawa and
Hiroaki Kobayashi},
editor = {Natalia Criado Pacheco and
Carlos Carrascosa and
Nardine Osman and
Vicente Juli{\'{a}}n Inglada},
title = {Proposal of an Action Selection Strategy with Expected Failure Probability
and Its Evaluation in Multi-agent Reinforcement Learning},
booktitle = {Multi-Agent Systems and Agreement Technologies - 14th European Conference,
{EUMAS} 2016, and 4th International Conference, {AT} 2016, Valencia,
Spain, December 15-16, 2016, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {10207},
pages = {172--186},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-59294-7\_15},
doi = {10.1007/978-3-319-59294-7\_15},
timestamp = {Thu, 08 Sep 2022 19:48:32 +0200},
biburl = {https://dblp.org/rec/conf/eumas/MiyazakiFK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ica2/MiyazakiFK16,
author = {Kazuteru Miyazaki and
Koudai Furukawa and
Hiroaki Kobayashi},
title = {Proposal and Evaluation of an Action Selection Strategy with Expected
Failure Probability in Multi-agent Learning},
booktitle = {{IEEE} International Conference on Agents, {ICA} 2016, Matsue, Japan,
September 28-30, 2016},
pages = {127--130},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.ieeecomputersociety.org/10.1109/ICA.2016.045},
doi = {10.1109/ICA.2016.045},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ica2/MiyazakiFK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bica/MiyazakiT14,
author = {Kazuteru Miyazaki and
Jun'ichi Takeno},
editor = {Alexei V. Samsonovich and
Paul Robertson},
title = {The Necessity of a Secondary System in Machine Consciousness},
booktitle = {5th Annual International Conference on Biologically Inspired Cognitive
Architectures, {BICA} 2014, Cambridge, MA, USA, November 7-9, 2014},
series = {Procedia Computer Science},
volume = {41},
pages = {15--22},
publisher = {Elsevier},
year = {2014},
url = {https://doi.org/10.1016/j.procs.2014.11.079},
doi = {10.1016/J.PROCS.2014.11.079},
timestamp = {Thu, 08 Jul 2021 14:29:22 +0200},
biburl = {https://dblp.org/rec/conf/bica/MiyazakiT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jcp/Miyazaki13,
author = {Kazuteru Miyazaki},
title = {Proposal of an Exploitation-oriented Learning Method on Multiple Rewards
and Penalties Environments and the Design Guideline},
journal = {J. Comput.},
volume = {8},
number = {7},
pages = {1683--1690},
year = {2013},
url = {http://www.jcomputers.us/index.php?m=content\&\#38;c=index\&\#38;a=show\&\#38;catid=90\&\#38;id=1187},
doi = {10.4304/JCP.8.7.1683-1690},
timestamp = {Thu, 25 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jcp/Miyazaki13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/Miyazaki12,
author = {Kazuteru Miyazaki},
title = {Proposal of the Continuous-Valued Penalty Avoiding Rational Policy
Making Algorithm},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {16},
number = {2},
pages = {183--190},
year = {2012},
url = {https://doi.org/10.20965/jaciii.2012.p0183},
doi = {10.20965/JACIII.2012.P0183},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/Miyazaki12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/KurodaMK12,
author = {Seiya Kuroda and
Kazuteru Miyazaki and
Hiroaki Kobayashi},
title = {Introduction of Fixed Mode States into Online Reinforcement Learning
with Penalties and Rewards and its Application to Biped Robot Waist
Trajectory Generation},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {16},
number = {6},
pages = {758--768},
year = {2012},
url = {https://doi.org/10.20965/jaciii.2012.p0758},
doi = {10.20965/JACIII.2012.P0758},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/KurodaMK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aciids/MiyazakiIK12,
author = {Kazuteru Miyazaki and
Masaki Itou and
Hiroaki Kobayashi},
editor = {Jeng{-}Shyang Pan and
Shyi{-}Ming Chen and
Ngoc Thanh Nguyen},
title = {Evaluation of the Improved Penalty Avoiding Rational Policy Making
Algorithm in Real World Environment},
booktitle = {Intelligent Information and Database Systems - 4th Asian Conference,
{ACIIDS} 2012, Kaohsiung, Taiwan, March 19-21, 2012, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7196},
pages = {270--280},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-28487-8\_28},
doi = {10.1007/978-3-642-28487-8\_28},
timestamp = {Thu, 16 Mar 2023 20:00:28 +0100},
biburl = {https://dblp.org/rec/conf/aciids/MiyazakiIK12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/scisisis/MiyazakiI12,
author = {Kazuteru Miyazaki and
Masaaki Ida},
title = {Proposal of an Active Course Classification Support system with Exploitation-oriented
Learning extended by positive and negative examples},
booktitle = {The 6th International Conference on Soft Computing and Intelligent
Systems (SCIS), and The 13th International Symposium on Advanced Intelligence
Systems (ISIS), Kobe, Japan, November 20-24, 2012},
pages = {1520--1527},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/SCIS-ISIS.2012.6505045},
doi = {10.1109/SCIS-ISIS.2012.6505045},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/scisisis/MiyazakiI12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/KurodaMK11,
author = {Seiya Kuroda and
Kazuteru Miyazaki and
Hiroaki Kobayashi},
editor = {Scott Sanner and
Marcus Hutter},
title = {Introduction of Fixed Mode States into Online Profit Sharing and Its
Application to Waist Trajectory Generation of Biped Robot},
booktitle = {Recent Advances in Reinforcement Learning - 9th European Workshop,
{EWRL} 2011, Athens, Greece, September 9-11, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7188},
pages = {297--308},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29946-9\_29},
doi = {10.1007/978-3-642-29946-9\_29},
timestamp = {Tue, 14 May 2019 10:00:48 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/KurodaMK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/MiyazakiI11,
author = {Kazuteru Miyazaki and
Masaaki Ida},
editor = {Scott Sanner and
Marcus Hutter},
title = {Proposal and Evaluation of the Active Course Classification Support
System with Exploitation-Oriented Learning},
booktitle = {Recent Advances in Reinforcement Learning - 9th European Workshop,
{EWRL} 2011, Athens, Greece, September 9-11, 2011, Revised Selected
Papers},
series = {Lecture Notes in Computer Science},
volume = {7188},
pages = {333--344},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-29946-9\_32},
doi = {10.1007/978-3-642-29946-9\_32},
timestamp = {Tue, 23 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/MiyazakiI11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ideal/Miyazaki10,
author = {Kazuteru Miyazaki},
editor = {Colin Fyfe and
Peter Ti{\~{n}}o and
Darryl Charles and
C{\'{e}}sar Ignacio Garc{\'{\i}}a{-}Osorio and
Hujun Yin},
title = {The Penalty Avoiding Rational Policy Making Algorithm in Continuous
Action Spaces},
booktitle = {Intelligent Data Engineering and Automated Learning - {IDEAL} 2010,
11th International Conference, Paisley, UK, September 1-3, 2010. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {6283},
pages = {178--185},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15381-5\_22},
doi = {10.1007/978-3-642-15381-5\_22},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/ideal/Miyazaki10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/MiyazakiK09,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
title = {Exploitation-Oriented Learning PS-r{\#}},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {13},
number = {6},
pages = {624--630},
year = {2009},
url = {https://doi.org/10.20965/jaciii.2009.p0624},
doi = {10.20965/JACIII.2009.P0624},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/MiyazakiK09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/WatanabeMK09,
author = {Takuji Watanabe and
Kazuteru Miyazaki and
Hiroaki Kobayashi},
title = {A New Improved Penalty Avoiding Rational Policy Making Algorithm for
Keepaway with Continuous State Spaces},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {13},
number = {6},
pages = {675--682},
year = {2009},
url = {https://doi.org/10.20965/jaciii.2009.p0675},
doi = {10.20965/JACIII.2009.P0675},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/WatanabeMK09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ideal/MiyazakiK08,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
editor = {Colin Fyfe and
Dongsup Kim and
Soo{-}Young Lee and
Hujun Yin},
title = {Proposal of Exploitation-Oriented Learning PS-r{\#}},
booktitle = {Intelligent Data Engineering and Automated Learning - {IDEAL} 2008,
9th International Conference, Daejeon, South Korea, November 2-5,
2008, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5326},
pages = {1--8},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-88906-9\_1},
doi = {10.1007/978-3-540-88906-9\_1},
timestamp = {Tue, 14 May 2019 10:00:45 +0200},
biburl = {https://dblp.org/rec/conf/ideal/MiyazakiK08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jaciii/MiyazakiK07,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
title = {Reinforcement Learning for Penalty Avoidance in Continuous State Spaces},
journal = {J. Adv. Comput. Intell. Intell. Informatics},
volume = {11},
number = {6},
pages = {668--676},
year = {2007},
url = {https://doi.org/10.20965/jaciii.2007.p0668},
doi = {10.20965/JACIII.2007.P0668},
timestamp = {Tue, 16 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jaciii/MiyazakiK07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ro-man/KatagamiNM06,
author = {Daisuke Katagami and
Katsumi Nitta and
Kazuteru Miyazaki},
title = {Multi User Learning Agent on the Distribution of MDPs},
booktitle = {The 15th {IEEE} International Symposium on Robot and Human Interactive
Communication, {RO-MAN} 2006, Hatfield, Herthfordshire, UK, 6-8 September,
2006},
pages = {698--703},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ROMAN.2006.314482},
doi = {10.1109/ROMAN.2006.314482},
timestamp = {Wed, 16 Oct 2019 14:14:50 +0200},
biburl = {https://dblp.org/rec/conf/ro-man/KatagamiNM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/alr/MiyazakiTK04,
author = {Kazuteru Miyazaki and
Sougo Tsuboi and
Shigenobu Kobayashi},
title = {Development of a reinforcement learning system to play Othello},
journal = {Artif. Life Robotics},
volume = {7},
number = {4},
pages = {177--181},
year = {2004},
url = {https://doi.org/10.1007/bf02471202},
doi = {10.1007/BF02471202},
timestamp = {Wed, 02 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/alr/MiyazakiTK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ngc/MiyazakiK01,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
title = {Rationality of Reward Sharing in Multi-agent Reinforcement Learning},
journal = {New Gener. Comput.},
volume = {19},
number = {2},
pages = {157--172},
year = {2001},
url = {https://doi.org/10.1007/BF03037252},
doi = {10.1007/BF03037252},
timestamp = {Thu, 14 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ngc/MiyazakiK01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/MiyazakiK00,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
title = {Reinforcement learning for penalty avoiding policy making},
booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man
{\&} Cybernetics: "Cybernetics Evolving to Systems, Humans, Organizations,
and their Complex Interactions", Sheraton Music City Hotel, Nashville,
Tennessee, USA, 8-11 October 2000},
pages = {206--211},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICSMC.2000.884990},
doi = {10.1109/ICSMC.2000.884990},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/smc/MiyazakiK00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isads/AraiMK99,
author = {Sachiyo Arai and
Kazuteru Miyazaki and
Shigenobu Kobayashi},
title = {Multi-agent Reinforcement Learning for Crane Control Problem: Designing
Rewards for Conflict Resolution},
booktitle = {The Fourth International Symposium on Autonomous Decentralized Systems,
{ISADS} 1999, Tokyo, Japan, March 20-23, 1999},
pages = {310--319},
publisher = {{IEEE} Computer Society},
year = {1999},
url = {https://doi.org/10.1109/ISADS.1999.838452},
doi = {10.1109/ISADS.1999.838452},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isads/AraiMK99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pricai/MiyazakiK99,
author = {Kazuteru Miyazaki and
Shigenobu Kobayashi},
editor = {Hideyuki Nakashima and
Chengqi Zhang},
title = {Rationality of Reward Sharing in Multi-agent Reinforcement Learning},
booktitle = {Approaches to Intelligent Agents, Second Pacific Rim International
Workshop on Multi-Agents, {PRIMA} '99, Kyoto, Japan, December 2-3,
1999, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {1733},
pages = {111--125},
publisher = {Springer},
year = {1999},
url = {https://doi.org/10.1007/3-540-46693-2\_9},
doi = {10.1007/3-540-46693-2\_9},
timestamp = {Tue, 14 May 2019 10:00:54 +0200},
biburl = {https://dblp.org/rec/conf/pricai/MiyazakiK99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/MiyazakiYK97,
author = {Kazuteru Miyazaki and
Masayuki Yamamura and
Shigenobu Kobayashi},
title = {k-Certainty Exploration Method: An Action Selector to Identify the
Environment in Reinforcement Learning},
journal = {Artif. Intell.},
volume = {91},
number = {1},
pages = {155--171},
year = {1997},
url = {https://doi.org/10.1016/S0004-3702(96)00062-8},
doi = {10.1016/S0004-3702(96)00062-8},
timestamp = {Sat, 27 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/MiyazakiYK97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KimuraMK97,
author = {Hajime Kimura and
Kazuteru Miyazaki and
Shigenobu Kobayashi},
editor = {Douglas H. Fisher},
title = {Reinforcement Learning in POMDPs with Function Approximation},
booktitle = {Proceedings of the Fourteenth International Conference on Machine
Learning {(ICML} 1997), Nashville, Tennessee, USA, July 8-12, 1997},
pages = {152--160},
publisher = {Morgan Kaufmann},
year = {1997},
timestamp = {Wed, 04 Dec 2002 12:34:29 +0100},
biburl = {https://dblp.org/rec/conf/icml/KimuraMK97.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2023-09-27 22:40 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
