MIYAZAKI Kazuteru

J-GLOBAL         Last updated: Oct 7, 2019 at 11:05
 
Avatar
Name
MIYAZAKI Kazuteru
Affiliation
National Institution for Academic Degrees and Quality Enhancement of Higher Education
Section
Department of Assessment and Research for Degree Awarding
Job title
Associate Professor
Degree
Doctor of Engineering(Tokyo Institute of Technology), Master of Engineering(Tokyo Institute of Technology)

Research Areas

 
 

Academic & Professional Experience

 
1996
 - 
1998
Tokyo Institute of Technology, Research Assistant
 
1998
 - 
1999
Tokyo Institute of Technology, Research Associate
 

Education

 
 
 - 
1996
Graduate School, Division of Integrated Science and Engineering, Tokyo Institute of Technology
 
 
 - 
1991
Faculty of Engineering, Meiji University
 

Published Papers

 
Proposal and Evaluation of Reward Sharing Method Based on Safety Level
KODAMA Naoki, MIYAZAKI Kazuteru, and KOBAYASHI Hiroaki
SICE Journal of Control, Measurement, and System Integration   11(3) 207-213   May 2018   [Refereed]
MIYAZAKI Kazuteru, FURUKAWA Koudai, and KOBAYASHI Hiroaki
Journal of Advanced Computational Intelligence and Intelligent Informatics   21(5) 930-938   Sep 2017   [Refereed]
MIYAZAKI Kazuteru
Journal of Advanced Computational Intelligence and Intelligent Informatics   21(5) 849-855   Sep 2017   [Refereed]
MURAOKA Hiroki, MIYAZAKI Kazuteru, KOBAYASHI Hiroaki
IEEJ Transactions on Electronics, Information and Systems   136(3) 273-281   Mar 2016   [Refereed]
MIYAZAKI Kazuteru and IDA Masaaki
大学評価・学位研究 第1 5 号 平成2 6 年3月(論文) [独立行政法人大学評価・学位授与機構] Research on Academic Degrees and University Evaluation   15 1-15   Mar 2014   [Refereed]
Kazuteru Miyazaki
JACIII   16(2) 183-190   Sep 2012   [Refereed]
Kazuteru Miyazaki,Shigenobu Kobayashi
JACIII   13(6) 624-630   Nov 2009   [Refereed]
Takuji Watanabe,Kazuteru Miyazaki,Hiroaki Kobayashi
JACIII   13(6) 675-682   Nov 2009   [Refereed]
宮崎 和光, 井田 正明, 芳鐘 冬樹, 野澤 孝之, 喜多 一
大学評価・学位研究 = RESEARCH ON ACADEMIC DEGREES AND UNIVERSITY EVALUATION   (6) 27-42   Dec 2007   [Refereed]
MIYAZAKI KAZUTERU, KIMURA HAJIME, KOBAYASHI SHIGENOBU
人工知能学会論文誌   22(3) 332-341   May 2007   [Refereed]
Reinforcement Learning is a kind of machine learning. We know Profit Sharing, the Rational Policy Making algorithm (RPM), the Penalty Avoiding Rational Policy Making algorithm and PS-r* to guarantee the rationality in a typical class of the Partia...
野澤 孝之, 芳鐘 冬樹, 井田 正明, 渋井 進, 宮崎 和光, 喜多 一, 川口 昭彦
大学評価・学位研究 = RESEARCH ON ACADEMIC DEGREES AND UNIVERSITY EVALUATION   (5) 37-54   Mar 2007   [Refereed]
Kazuteru Miyazaki,Shigenobu Kobayashi
JACIII   11(6) 668-676   Jul 2007   [Refereed]
YOSHIKANE FUYUKI, IDA MASAAKI, NOZAWA TAKAYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
知能と情報   18(2) 299-309   Apr 2006   [Refereed]
As syllabi are very important documents that inform people, particularly students, of the contents of curricula in detail, the techniques for efficient retrieval of them are in keen demand. It is necessary for efficient retrieval to arrange the re...
MIYAZAKI KAZUTERU, IDA MASAAKI, YOSHIKANE FUYUKI, NOZAWA TAKAYUKI, KITA HAJIME
知能と情報   17(5) 558-568   Oct 2005   [Refereed]
The National Institution for Academic Degrees and University Evaluation is engaged in the awarding of academic degrees based on the accumulation of credits. These credits must be classified according to pre-determined criteria for the chosen disci...
NOZAWA TAKAYUKI, IDA MASAAKI, YOSHIKANE FUYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
知能と情報   17(5) 569-586   Oct 2005   [Refereed]
Comprehending the features of curricula provided by various higher education institutions is significant in designing and evaluating a curriculum. To facilitate comprehension of the curricula's features, Curriculum Analyzing System has been develo...
神谷 武志, 宮崎 和光, 森 利枝
大学評価・学位研究 = RESEARCH ON ACADEMIC DEGREES AND UNIVERSITY EVALUATION   (2) 101-111   Mar 2005   [Refereed]
井田 正明, 野澤 孝之, 芳鐘 冬樹, 宮崎 和光, 喜多 一
大学評価・学位研究 = RESEARCH ON ACADEMIC DEGREES AND UNIVERSITY EVALUATION   (2) 87-97   Mar 2005   [Refereed]
芳鐘 冬樹, 井田 正明, 野澤 孝之, 宮崎 和光, 喜多 一
大学評価・学位研究 = RESEARCH ON ACADEMIC DEGREES AND UNIVERSITY EVALUATION   (1) 135-143   Mar 2005   [Refereed]
MIYAZAKI KAZUTERU, IDA MASAAKI, YOSHIKANE FUYUKI, NOZAWA TAKAYUKI, KITA HAJIME
情報処理学会論文誌   46(3) 782-791   Mar 2005   [Refereed]
大学評価・学位授与機構では,短期大学・高等専門学校卒業者および専門学校修了者等を対象に,単位累積加算を基にした学士の学位授与事業を行っている.この制度を利用し学士の学位授与を希望するする者は,各専門分野ごとに定められた所定の単位を修得しなければならない.申請者は,自らの判断で修得した科目を分類・整理し申告する.それに対し,大学評価・学位授与機構では,申請者による分類の正しさを,各専門分野の専門委員が申告された科目のシラバスを読むことで検討している.しかしながら,近年の申請者数の増大から,こ...
芳鐘冬樹, 井田正明, 野澤孝之, 宮崎和光, 喜多一
名古屋大学附属図書館研究年報   3(3) 15-22   Mar 2005   [Refereed]
NOZAWA TAKAYUKI, IDA MASAAKI, YOSHIKANE FUYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
情報処理学会論文誌   46(1) 289-300   Jan 2005   [Refereed]
高等教育機関が独創的なカリキュラムを設計しようとする場合や,第三者が高等教育機関のカリキュラムの特徴を評価する場合,多数の教育機関にまたがる教育内容の横断的な把握が必要となる.しかしこれは専門家にとっても負荷の高い課題であり,カリキュラム設計や評価の方針を立てやすくするためのコンピュータを用いた支援環境が望まれる.本研究では,共通形式化されたシラバスデータを対象に,それらが含む専門用語を抽出し,その出現頻度に基づき科目間の類似度を計算しクラスタリングを行い,多角的な分類軸に沿って科目のクラ...
Kazuteru Miyazaki, Sougo Tsuboi, and Shigenobu Kobayashi
Artificial Life and Robotics   17(4) 177-181   Apr 2004   [Refereed]
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
人工知能学会論文誌   18 286-296   Nov 2003   [Refereed]
We know the rationality theorem of Profit Sharing(PS) [Miyazaki 94, Miyazaki 99b] and the Rational Policy Making algorithm(RPM) [Miyazaki 99a] to guarantee the rationality in a typical class of Partially Observable Markov Decision Pr...
宮崎和光, 坪井創吾, 小林重信
人工知能学会論文誌   17 548-556   Nov 2002   [Refereed]
The purpose of reinforcement learning is to learn an optimal policy in general. However, in 2-players games such as the othello game, it is important to acquire a penalty avoiding policy. In this paper, we focus on formation of a penalty avoiding ...
宮崎和光, 坪井創吾, 小林重信
人工知能学会論文誌   16 185-192   Nov 2001   [Refereed]
Reinforcement learning is a kind of machine learning. It aims to adapt an agent to a given environment with a clue to rewards. In general, the purpose of reinforcement learning system is to acquire an optimum policy that can maximize expected rewa...
Kazuteru Miyazaki,Shigenobu Kobayashi
New Generation Comput.   19(2) 157-172   Jun 2001   [Refereed]
Controlling Multiple Cranes Using Multi-Agent Reinforcement Learning: Emerging Coordination among Competitive Agents
Arai, S., Miyazaki, K. and Kobayashi, S.
IEICE Transactions on Communications   E-83-B(5) 1039-1047   May 2000   [Refereed]
MIYAZAKI KAZUTERU, ARAI SACHIYO, KOBAYASHI SHIGENOBU
人工知能学会誌   14(6) 1156-1164   Nov 1999   [Refereed]
Most of multi-agent systems have been developed in the field of Distributed Artificial Intelligence (DAI) whose schemes are based on plenty of pre-knowledge of the agents' world or organized relationships among the agents. However, these kind of k...
MIYAZAKI KAZUTERU, ARAI SACHIYO, KOBAYASHI SHIGENOBU
人工知能学会誌   14(1) 148-156   Jan 1999   [Refereed]
Partially Observable Markov Decision Process (POMDP) is a representative class of non-Markovian environments, where agents sense different environmental states as the same sensory input. We recognize that full implementation of POMDPs must overcom...
ARAI SACHIYO, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
人工知能学会誌   13(4) 609-618   Jul 1998   [Refereed]
Most of multi-agent systems have been developed in the field of Distributed Artificial Intelligence (DAI) whose schemes are based on plenty of pre-knowledge of the agents' world or organized relationships among the agents. However, these kind of k...
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
人工知能学会誌   12(1) 78-89   Jan 1997   [Refereed]
Reinforcement learning is a kind of machine learning. It aims to adapt an agent to a given environment with a clue to rewards. Profit sharing (PS) can get rewards efficiently at an initial learning phase. However, it can not always learn an optimu...
Kazuteru Miyazaki,Masayuki Yamamura,Shigenobu Kobayashi
Artif. Intell.   91(1) 155-171   1997   [Refereed][Invited]
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
人工知能学会誌   11(5) 804-808   Sep 1996   [Refereed]
k-Certainty Exploration Method gives top priority for selection to an action whose number of selection is the fewest. However it doesn't consider any state-transition probability. Therefore, though it guarantees the rationality and the efficiency ...
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
人工知能学会誌   10(3) 454-463   May 1995   [Refereed]
Reinforcement learning aims to adapt a system to an unkown environment according to rewards. There are two issues to handle delayed reward and uncertainty. Q-learning is a representative reinforcement learning method. It is used by many works sinc...
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
人工知能学会誌   9(4) 580-587   Jul 1994   [Refereed]
Reinforcement learning is a kind of machine learning. It aims to adapt a system to a given environment according to rewards. We consider profit sharing that is a representative reinforcement learning method. A rule sequence applied between reward ...

Misc

 
Research on Consistency between Diploma Policies and Nomenclature of Major Disciplines : Deep Learning Approach
MIYAZAKI Kazuteru, TAKAHASHI Nozomi, and MORI Rie
2019 7th International Conference on Information and Education Technology (ICIET2019)   to appear   Mar 2019   [Refereed]
Consistency Assessment between Diploma Policy and Curriculum Policy using Character-level CNN
MIYAZAKI Kazuteru, and IDA Masaaki
Joint 10th International Conference on Soft Computing and Intelligent Systems and 19th International Symposium on Advanced Intelligent Systems (SCIS&ISIS2018)      Dec 2018   [Refereed]
KODAMA Naoki, MIYAZAKI Kazuteru, and HARADA Taku
2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA2018)   983-988   Nov 2018   [Refereed]
SHIRAISHI Daisuke, MIYAZAKI Kazuteru, and KOBAYASHI Hiroaki
Lecture Notes in Computer Science (International Conference on Principles and Practice of Multi-Agent Systems (PRIMA2018))   11224 638-645   Oct 2018   [Refereed]
MIYAZAKI Kazuteru, KODAMA Naoki, and KOBAYASHI Hiroaki
IntelliSys 2018   187-200   Sep 2018   [Refereed]
MIZUNO Daisuke, MIYAZAKI Kazuteru, and KOBAYASHI Hiroaki
Biologically Inspired Cognitive Architectures Meeting   228-233   Aug 2018   [Refereed]
MIYAZAKI Kazuteru
Procedia Computer Science (2017 Annual International Conference on Biologically Inspired Cognitive Architectures (BICA 2017))   123 302-307   2018   [Refereed]
Kazuteru Miyazaki, Koudai Furukawa and Hiroaki Kobayashi
Lecture Notes in Computer Science 「Multi-Agent Systems and Agreement Technologies」, 14th European Conference on Multi-Agent Systems   10207    Jun 2017   [Refereed]
MIYAZAKI Kazuteru
Procedia Computer Science (2016 Annual International Conference on Biologically Inspired Cognitive Architectures (BICA 2016))   88 94-101   Dec 2016   [Refereed]
Kazuteru Miyazaki, Koudai Furukawa and Hiroaki Kobayashi
International Workshop on Multiagent Learning: Theory and Applications   127-130   Sep 2016   [Refereed]
The Necessity of a Secondary System in Multi-agent Learning
MIYAZAKI Kazuteru
The First International Symposium on Swarm Behavior and Bio-Inspired Robotics   299-305   Oct 2015   [Refereed]
MIYAZAKI Kazuteru
International Journal of Machine Learning and Computing (2014 International Conference on Artificial Intelligence (ICOAI 2014))   5(2) 121-126   Apr 2015   [Refereed]
Kazuteru Miyazaki,Jun'ichi Takeno
Procedia Computer Science (2014 Annual International Conference on Biologically Inspired Cognitive Architectures (BICA 2014))   41 15-22   Dec 2014   [Refereed]
MIYAZAKI Kazuteru, Ida Masaaki
SICE Annual Conference 2014   928-934   Sep 2014   [Refereed]
宮崎和光, 井田正明
知能と情報   26(2) 42-50   Apr 2014
Proposal of a Propagation Algorithm of the Expected Failure Probability and the Effectiveness on Multi-agent Environment
Kazuteru Miyazaki, Hiroki Muraoka, Hiroaki Kobayashi
   Sep 2013   [Refereed]
MIYAZAKI Kazuteru
計測と制御 = Journal of the Society of Instrument and Control Engineers   52(5) 462-467   May 2013
Proposal of an Exploitation-oriented Learning Method on Multiple Rewards and Penalties Environments
Kazuteru Miyazaki
The 2nd International Conference on Applied and Theoretical Information Systems Research (2nd ATISR)      Dec 2012   [Refereed]
Kazuteru Miyazaki, Masaaki Ida
The 6th International Conference on Soft Computing and Intelligent Systems and the 13th International Symposium on Advanced Intelligent Systems (SCIS-ISIS 2012)      Nov 2012   [Refereed]
Kazuteru Miyazaki,Masaki Itou,Hiroaki Kobayashi
Intelligent Information and Database Systems - 4th Asian Conference, ACIIDS 2012, Kaohsiung, Taiwan, March 19-21, 2012, Proceedings, Part I, Lecture Notes in Computer Science   7196 270-280   2012   [Refereed]
Kazuteru Miyazaki,Masaaki Ida
Recent Advances in Reinforcement Learning - 9th European Workshop, EWRL 2011, Athens, Greece, September 9-11, 2011, Revised Selected Papers, Lecture Notes in Computer Science   7188 333-344   2011   [Refereed]
Seiya Kuroda,Kazuteru Miyazaki,Hiroaki Kobayashi
Recent Advances in Reinforcement Learning - 9th European Workshop, EWRL 2011, Athens, Greece, September 9-11, 2011, Revised Selected Papers, Lecture Notes in Computer Science   7188 297-308   2011   [Refereed]
Kazuteru Miyazaki
Intelligent Data Engineering and Automated Learning - IDEAL 2010, 11th International Conference, Paisley, UK, September 1-3, 2010. Proceedings   178-185   Sep 2010   [Refereed]
Threshold learning in the improved penalty avoiding rational policy making algorithm
Kazuteru Miyazaki, Ryouhei Kobayashi, Hiroaki Kobayashi
SICE Annual Conference 2010   3240-3245   Aug 2010   [Refereed]
Automatic Tuning of Judgement Parameter in Continuous State Exploitation-oriented Learning
MIYAZAKI Kazuteru
SICE Annual Conference 2010   3246-3249   Aug 2010   [Refereed]
Development of the Active Course Classification Support System with a Learning Mechanism
Miyazaki, K., Yoshikane, F. and Ida, M.
ICROSS-SICE International Joint Conference 2009 (ICCAS-SICE 2009)   1189-1194   Aug 2009   [Refereed]
A New Improved Penalty Avoiding Rational Policy Making Algorithm for Keepaway with Continuous State Space
Takuji Watanabe, Kazuteru Miyazaki, Hiroaki Kobayashi
   2009   [Refereed]
Consideration on Document Structure of Syllabi - Advanced Engineering Programs of Colleges of Technology
M. Ida, K. Miyazaki
SCIS&ISIS 2008   172-175   Sep 2008   [Refereed]
T. Watanabe, K. Miyazaki, H. Kobayashi
SICE Annual Conference 2008   2039-2044   Aug 2008   [Refereed]
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
Intelligent Data Engineering and Automated Learning–IDEAL 200   1-8   2008   [Refereed]
Proposal and Evaluation of the Penalty Avoiding Rational Policy Making Algorithm with Penalty Level
MMiyazaki, K., Kojima, T. and Kobayashi, H.
International Conference on Instrumentation, Control and Information 2007 (SICE Annual Conference 2007)   2766-2773   Sep 2007   [Refereed]
Improvement of the Penalty Avoiding Rational Policy Making algorithm to Real World Robotics
Miyazaki, K., Namatame, T., Kojima, T. and Kobayashi, H.
3th International Conference on Advanced Robotics (ICAR 2007)   1183-1188   Aug 2007   [Refereed]
宮崎和光
人工知能学会誌   21(5) 517-521   Sep 2006
YOSHIKANE FUYUKI, IDA MASAAKI, NOZAWA TAKAYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
電子情報通信学会技術研究報告   105(298(ET2005 27-37)) 53-58   Sep 2005
As syllabi play an important role as information sources in course selection by students in universities. We have been developing a system for efficient retrieval of syllabi to support users of them. In the developing system, the results of retrie...
Reinforcement Learning in Multiple Rewards and Penalties Environments (jointly worked)
Joint 2nd International Conference on Soft Computing and Intelligent Systems and 5th International Symposium on Advanced Intelligent Systems   CD-ROM    2004
KITA Hajime, MIYAZAKI Kazuteru
Systems, control and information   47(9) 457-458   Sep 2003
Generating Cooperative Behavior by Multi-Agent Profit Sharing on the Soccer Game (jointly worked)
The 4th International Symposium on Advanced Intelligent Systems   166-169   2003
On Development of a Course Classification System using Syllabus Data (jointly worked)
1st Asia-Pacific International Conference on Computational Methods in Engineering   68-69   2003
Reinforcement Learning in 2-players games(jointly worked)
Proc. of the 7th International Symposium on Artificial Life and Robotics   183-186   2002
Learning Robust Policies for Uncertain and Stochastic Multi-agent Domains(jointly worked)
Proc. of the 7th International Symposium on Artificial Life and Robotics   179-182   2002
Comparioson with Profit Sharing and Random Selection in POMDPs(jointly worked)
Proc.of Joint 1st International Conference on Soft Computing and Intelligent Systems   24Q6-2(CD-ROM)    2002
Reinforcement Learning for Penalty Avoiding Profit Sharing and its Application to the Soccer Game(jointly worked)
Proc. of ICONIP'02-SEAL'02-FSKD'02   335-339   2002
Educational Issues of Information Technology (IT) Engineers in Japan - Gap between Industrial Demand and University Supply ? (jointly worked)
2002 ASEE/SEFI/TUB International Colloquium "Global Changes in EngineeringEducation"   Poster Presentation    2002
Rationality of Reward Sharing in Multi-agent Reinforcement Learning(jointly worked)
New Generation Computing   19(2) 157-172   2001
Reinforcement Learning for Penalty Avoiding Policy Making and its Extensions and an Applications to the Othello Game(jointly worked)
Proc. of the 7th International Conference on Information System Analysis and Cynthesis   3 40-44   2001
International Conference on Computational Intelligence and Multimedia Application 2001   123-127   2001
Cranes Contral Using Multi-agent Profit Sharing
6th International Conference on Information Systems Analysis and Cynthesis   IX 178-183   2000
Reinforcement Learning for Penalty Avoiding Policy Making(jointly worked)
2000 IEEE International Conference on Systems, Man, and Cybernetics   206-211   2000
Kazuteru Miyazaki,Shigenobu Kobayashi
Approaches to Intelligent Agents, Second Pacific Rim International Workshop on Multi-Agents, PRIMA '99, Kyoto, Japan, December 2-3, 1999, Proceedings   111-125   1999   [Refereed]
Sachiyo Arai,Kazuteru Miyazaki,Shigenobu Kobayashi
The Fourth International Symposium on Autonomous Decentralized Systems, ISADS 1999, Tokyo, Japan, March 20-23, 1999   310-319   1999   [Refereed]
Proposal for an Algorithm to Improve a Rational Policy in POMDPs(jointly worked)
1999 IEEE International Conference on Systems, Man and Cybernetics   492-497   1999
On the Rationality of Profit Sharing in Partially Observable Markov Decision Processes(jointly worked)
5th International Conference on Information Systems Analysis and Cynthesis   190-197   1999
Rationality of Reward Sharing in Multi-agent Reinforcement Learning(jointly worked)
Second Pacific Rim International Workshop on Multi-Agents   111-125   1999
Multi-agent Reinforcement Learning for Crane Control Problem: DesigningRewards for Conflict Resolution (jointly worked)
The 4th International Symposium on Autonomous Decentralized Systems   310-319   1999
Learning Deterministic Policies in Partially Observable Markov Decision Processes(jointly worked)
International Conference on Intelligent Autonomous System 5   250-257   1998
Cranes Control Using Multi-agent Reinforcement Leaning(jointly worked)
International Conference on Intelligent Autonomous System 5   335-342   1998
Miyazaki Kazuteru, Kobayashi Shigenobu
Journal of Japanese Society for Artificial Intelligence   12(6) 811-821   Nov 1997
MASUO ATSUSHI, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報合同シンポジウム講演論文集   1997 117-122   Nov 1997
MIYAZAKI KAZUTERU
日本ファジィ学会誌   9(4) 447-450   Aug 1997
Hajime Kimura,Kazuteru Miyazaki,Shigenobu Kobayashi
Proceedings of the Fourteenth International Conference on Machine Learning (ICML 1997), Nashville, Tennessee, USA, July 8-12, 1997   152-160   1997   [Refereed]
Reinforcement Learning in POMDPs with Function Approximation(jointly worked)
Proceedings of the 14th International Conference on Machine Learning   152-160   1997
Generationg Cooperative Behavior by Multi-Agent Reinforcement Learning(jointly worked)
Proc. of the 6th European Workshop on Learning Robots   143-157   1997
Marcopolo : A Reinforcement Learning System considering tradeoff exploration and exploitation under Marcovian Environments(jointly worked)
Proceedong of IIZUKA '96   561-564   1996
Yamamura Masayuki, Miyazaki Kazuteru, Kobayashi Shigenobu
Journal of Japanese Society for Artificial Intelligence   10(5) 683-689   Sep 1995
YAMAMURA Masayuki, MIYAZAKI Kazuteru, KOBAYASHI Shigenobu
システム/制御/情報 : システム制御情報学会誌 = Systems, control and information   39(4) 191-196   Apr 1995
On the Rationarity of Profit Sharing in Reinforcement Learning (jointly worked)
The 3rd International Conference on Fuzy Logic, Neural Nets and Soft Computing   285-288   1994

Books etc

 
On development of a course classification support system using syllabus data (jointly worked)
Computational Engineering I   2004   

Conference Activities & Talks

 
A Proposal of Exploitation-oriented Deep Reinforcement Learning Method with Double Episode
KODAMA Naoki, HARADA Taku, and MIYAZAKI Kazuteru
Sep 2018   
Experimental Results of Exploitation-oriented Learning with Deep Learning
MIYAZAKI Kazuteru
Dec 2016   
Exploitation-oriented Learning XoL with Deep Learning - Comparison with a deep Q-network-
MIYAZAKI Kazuteru
The Papers of Technical Meeting on "Systems", IEE Japan   Jul 2016   
Proposal of 2 reward PS reinforcement learning method and verification of the efficiency
KODAMA Naoki, MIYAZAKI Kazuteru, KOBAYASHI Hiroaki
The Papers of Technical Meeting on "Systems", IEE Japan   Jul 2016   
Proposal and Evaluation of an Action Selection with Expected Failure Probability in Multi-agent Learning
FURUKAWA Koudai, MIYAZAKI Kazuteru, KOBAYASHI Hiroaki
A Study of an Indirect Reward on Multi-agent Environments   Mar 2016   
The Result of Follow-up Surveys to the Earners of a Bachelor Degree of NIAD-UE
MIYAZAKI Kazuteru
The Papers of Technical Meeting on "Systems", IEE Japan   Jun 2015   
FURUKAWA KODAI, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
自律分散システム・シンポジウム(CD-ROM)   22 Jan 2015   
宮崎和光
情報科学技術フォーラム講演論文集   19 Aug 2014   
MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
電気学会システム研究会資料   27 Jun 2013   
村岡宏紀, 宮崎和光, 小林博明
知能システムシンポジウム資料   14 Mar 2013   
宮崎和光, 井田正明
自動制御連合講演会(CD-ROM)   2013   
宮崎和光
電気学会電子・情報・システム部門大会講演論文集(CD-ROM)   5 Sep 2012   
宮崎和光
知能システムシンポジウム資料   15 Mar 2012   
伊藤大貴, 岡島勇也, 田中純夫, 小林博明, 宮崎和光
自動制御連合講演会(CD-ROM)   19 Nov 2011   
In this paper, we discuss on the efficiency improvement of reinforcement learning by introducing fixed mode states. For a long term learning problem such as the waist trajectory generation of biped robots, the learning efficiency is significantly ...
村岡宏紀, 宮崎和光, 小林博明
自動制御連合講演会(CD-ROM)   19 Nov 2011   
本報告は罰と報酬を用いる強化学習において、新たに失敗確率の伝播法を提案しその有効性を確認する。学習の効率化を図るためには少ない試行数で罰ルールを発見し回避する事が有効である。そこで、失敗確率をルール上で伝播させる事によって、そのルールの将来失敗する確率を推定し、少ない試行数で罰ルールを発見する手法を提案し、迷路問題を用いたシミュレーションによってその有効性を示す。
宮崎和光, 井田正明
知能システムシンポジウム資料   16 Mar 2011   
伊藤昌樹, 宮崎和光, 小林博明
自動制御連合講演会(CD-ROM)   3 Nov 2010   
本研究では,著者らが提案する「改良型罰回避政策形成アルゴリズム」をマルチエージェント系の連続タスクである「Keepaway task」に適用し,シミュレーションにより最適な報酬割引率・罰ルール度閾値の選定を行う.その後,シミュレーションで最も学習効果の見られた報酬割引率・罰ルール度閾値を用いた実機実験を行うことで,実環境での学習性能を検証する。
宮崎和光
知能システムシンポジウム資料   16 Mar 2010   
Kobayashi Ryohei, Miyazaki Kazuteru, Kobayashi Hiroaki
日本機械学会関東支部総会講演会講演論文集   9 Mar 2010   
Penalty Avoiding Rational Policy Making algorithm (PARP) based on Profit Sharing method and was planed to learn a penalty avoiding policy. PARP is improved to save memories and to cope with uncertainties. The efficiency of the Improved Penalty Avo...
MIYAZAKI KAZUTERU, YOSHIKANE FUYUKI, IDA MASAAKI
知能システムシンポジウム資料   Mar 2009   
KOBAYASHI RYOHEI, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
自動制御連合講演会(CD-ROM)   2009   
改良型罰回避政策形成アルゴリズムでは、閾値γを用いて罰基底の判定を行う。一般に、γは、学習結果に大きな影響を与えることが知られている。これまでは、予備的実験等を通じて、適切なγを事前に設定する必要があった。それに対し本研究では、マルチスタート法を活用し、γを学習する手法を提案する。提案手法を、サッカーの試合におけるパス回しをモデルにしたベンチマーク問題であるkeepawayタスクへ適用し、有効性を確認する。
井田正明, 宮崎和光
ファジィ・ワークショップ講演論文集   7 Mar 2008   
RYUZAKI MASATO, KOBAYASHI HIROAKI, MIYAZAKI KAZUTERU
自動制御連合講演会(CD-ROM)   2008   
To find optimal joint stiffness for a given task is important but difficult in general.In this paper, the optimal joint stiffness of a tendon-driven robotic arm for a force-posetion hybrid control task is acquired using reinforcement learning bas...
経験強化型学習PS-r#の提案
宮崎和光, 小林重信
第35回知能システムシンポジウム   2008   
WATANABE TAKUJI, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
日本ロボット学会学術講演会予稿集(CD-ROM)   13 Sep 2007   
野沢孝之, 渋井進, 芳鐘冬樹, 井田正明, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   6 Mar 2007   
井田正明, 野澤孝之, 宮崎和光, 芳鐘冬樹, 渋井進, 喜多一
情報処理学会全国大会講演論文集   6 Mar 2007   
NEHASHI Tsuyoshi, MIYAZAKI Kazuteru, TAKADAMA Keiki
自律分散システム・シンポジウム資料 = SICE Symposium on Decentralized Autonomous Systems   29 Jan 2007   
MIYAZAKI KAZUTERU, IDA MASAAKI, YOSHIKANE FUYUKI, NOZAWA TAKAYUKI, SHIBUI SUSUMU, KITA HAJIME
知能システムシンポジウム資料   2007   
KOJIMA TOMOMIZU, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
日本ロボット学会学術講演会予稿集(CD-ROM)   14 Sep 2006   
MIYAZAKI KAZUTERU, NAMATAME TAKUYA, KOBAYASHI HIROAKI
知能システムシンポジウム資料   2006   
KATAGAMI DAISUKE, NITTA KATSUMI, MIYAZAKI KAZUTERU
人工知能学会全国大会論文集(CD-ROM)   2006   
NAMETAME TAKUYA, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
自動制御連合講演会(CD-ROM)   25 Nov 2005   
マルチエージェント環境下での自律分散型ロボットの協調行動の獲得のために強化学習を用いた研究がなされている。本研究ではサッカーゲームを題材とし、敵が存在する中でのエージェント間のパス行動を採り上げる。手法として強化学習法のひとつであるProfit Sharingを用いてシミュレーションを行い実際のロボットにパス行動獲得を実現することを目的とする。
井田正明, 野沢孝之, 芳鐘冬樹, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   2 Mar 2005   
芳鐘冬樹, 井田正明, 野沢孝之, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   2 Mar 2005   
井田正明, 芳鐘冬樹, 野沢孝之, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   2 Mar 2005   
宮崎 和光, 小林 重信
人工知能学会全国大会論文集   2005   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報部門学術講演会講演論文集   2005   
NIDE NAOYUKI, TAKATA SHIRO, YAMAKAWA HIROSHI, MIYAZAKI KAZUTERU, OTA MASAYUKI
人工知能学会全国大会論文集(CD-ROM)   2005   
井田正明, 野沢孝之, 芳鐘冬樹, 宮崎和光, 喜多一
情報科学技術フォーラム   20 Aug 2004   
Miyazaki Kazuteru, Ida Masaaki, Yoshikane Fuyuki, Nozawa Takayuki, Kita Hajime
情報科学技術フォーラム一般講演論文集   20 Aug 2004   
芳鐘冬樹, 井田正明, 宮崎和光, 野沢孝之, 喜多一
情報処理学会全国大会講演論文集   9 Mar 2004   
野沢孝之, 井田正明, 芳鐘冬樹, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   9 Mar 2004   
井田正明, 芳鐘冬樹, 野沢孝之, 宮崎和光, 喜多一
情報処理学会全国大会講演論文集   9 Mar 2004   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報部門学術講演会講演論文集   2004   
TAKATA SHIRO, YAMAKAWA HIROSHI, MIYAZAKI KAZUTERU, NIIDE NAOYUKI, NAGAYUKI YASUO, SAKAI TAKAMICHI
人工知能学会全国大会論文集(CD-ROM)   2004   
IDA MASAAKI, NOZAWA TAKAYUKI, YOSHIKANE FUYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
システム・情報部門学術講演会講演論文集   2004   
IDA MASAAKI, YOSHIKANE FUYUKI, NOZAWA TAKAYUKI, MIYAZAKI KAZUTERU, KITA HAJIME
システム制御情報学会研究発表講演会講演論文集   2004   
宮崎和光, 井田正明, 芳鐘冬樹, 喜多一
情報科学技術フォーラム   25 Aug 2003   
井田正明, 宮崎和光, 芳鐘冬樹, 喜多一
情報処理学会全国大会講演論文集   25 Mar 2003   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報部門学術講演会講演論文集   2002   
TERADA TADASHI, MIYAZAKI KAZUTERU, KOBAYASHI HIROAKI
自動制御連合講演会講演論文集   2002   
MIYAZAKI KAZUTERU, SAITO JUMPEI, KOBAYASHI HIROAKI
自動制御連合講演会講演論文集   2002   
TSUZAKI SHIHO, ARAI SACHIYO, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
知能システムシンポジウム資料   2001   
MIYAZAKI KAZUTERU
日本機械学会機械力学・計測制御部門講演会論文集   Sep 2000   
TSUBOI SOGO, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
知能システムシンポジウム資料   23 Mar 2000   
MIYAZAKI KAZUTERU, ISHIHARA SHUICHI, ARAI SACHIYO, KOBAYASHI SHIGENOBU
自律分散システム・シンポジウム資料   18 Jan 1999   
TSUBOI SHOGO, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
知能システムシンポジウム資料   19 Mar 1998   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
知能システムシンポジウム資料   19 Mar 1998   
ARAI SACHIYO, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム制御情報学会研究発表講演会講演論文集   1998   
TSUBOI Sougo, MIYAZAKI Kazuteru, KOBAYASHI Shigenobu
知能システムシンポジウム資料   18 Mar 1997   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
自律分散システム・シンポジウム資料   16 Jan 1997   
KIMURA HAJIME, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
自律分散システム・シンポジウム資料   16 Jan 1997   
MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報合同シンポジウム講演論文集   Oct 1996   
YAMAMURA MASAYUKI, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報合同シンポジウム講演論文集   Oct 1996   
KIMURA HAJIME, MIYAZAKI KAZUTERU, KOBAYASHI SHIGENOBU
システム・情報合同シンポジウム講演論文集   Oct 1996   
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
自律分散システム・シンポジウム資料   17 Jan 1996   
YAMAMURA MASAYUKI, MIYAZAKI KAZUTERU, IWASHITA TAKEHISA, KOBAYASHI SHIGENOBU
自律分散システム・シンポジウム資料   Jan 1995   
KOBAYASHI SHIGENOBU, YAMAMURA MASAYUKI, MIYAZAKI KAZUTERU
人工知能学会全国大会論文集   20 Jun 1994   
MIYAZAKI KAZUTERU, YAMAMURA MASAYUKI, KOBAYASHI SHIGENOBU
システムシンポジウム講演論文集   1993   
宮崎和光, 山村雅幸, 小林重信
システムシンポジウム講演論文集   1992   

Research Grants & Projects

 
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(C))
Project Year: Apr 2017 - Mar 2020    Investigator(s): Kazuteru Miyazaki
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(C))
Project Year: 2014 - 2016    Investigator(s): Kazuteru Miyazaki
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(C))
Project Year: 2010 - 2012    Investigator(s): Kazuteru MIYAZAKI
This research has completed an Exploitation-oriented Learning (XoL) method that can treat multiple rewards and penalties. Furthermore the design guideline of rewards and penalties on the XoL method has been proposed through illustrative examples, ...
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(C))
Project Year: 2009 - 2011    Investigator(s): Hiroaki KOBAYASHI
In this research, a learning method for robots to learn appropriate actions by profits and penalties given from the environment was developed and applied to action learning in the robotic succor game and walking movement of a biped robot. To apply...
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(B))
Project Year: 2007 - 2009    Investigator(s): 橋本 弘信, Yoshiko TAKITA
2005 Report of the Central Council for Education entitled "Graduate Education in the New Era" recommends that master's courses develop not only researchers, high-skill professionals and university professors but intellectual human resources that a...