MAKINO Takaki 牧野貴樹

Researcher Number	20418651
Affiliation (based on the past Project Information) *help	2013: 東京大学, 生産技術研究所, 特任准教授 2010: 東京大学, 生産技術研究所, 特任准教授 2008 – 2010: 東京大学, 総括プロジェクト機構, 特任助教 2008: The University of Tokyo, 大学院・新領域創成科学研究科, 特任助教
Review Section/Research Field	Principal Investigator Intelligent informatics / Intelligent informatics Except Principal Investigator Bioinformatics/Life informatics
Keywords	Principal Investigator 逆強化学習 / 徒弟学習 / 強化学習 / LUKE / エルマンネット / 予測的状態表現 / 部分観測マルコフ決定過程 / ベイズ推定 / サンプリング法 / 階層的クラスタリング … More / 隠れマルコフモデル / ノンパラメトリックベイズ / TD-Network / 中華料理店過程 / クラスタリング / 無限隠れマルコフモデル / ベイズ推論 / Restricted Collapsed Draws … More Except Principal Investigator シナプス / 神経ネットワーク / シナプス分解能 / X線顕微鏡 / コネクトーム / ニューロインフォマティクス / 神経回路網 Less

環境モデル徒弟学習の抜本的高速化技術の開発と実用的対話システムのプロトタイプ構築Principal Investigator
- Principal Investigator
  
  牧野貴樹
- Project Period (FY)
  2013
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
Connectome Project X: X-ray microscopy revealing neuronal wiring diagram
- Principal Investigator
  
  MIZUTANI Haruo
- Project Period (FY)
  2008 – 2010
- Research Category
  
  Grant-in-Aid for Scientific Research on Innovative Areas (Research a proposed research project)
- Research Field
  
  Bioinformatics/Life informatics
- Research Institution
  The University of Tokyo
Computational Theory of Inductive Reinforcement Learning-Bayesian Inference on Environment Search and Inductive ReconstructionPrincipal Investigator
- Principal Investigator
  
  MAKINO Takaki
- Project Period (FY)
  2008 – 2010
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo

All 2014 2013 2012 2011 2010 2009 2008

All Journal Article Presentation Book Patent

[Book] コミュニケーションの自己組織化. 国武豊喜 (監修), 自己組織化ハンドブック2009
- Author(s)
  牧野貴樹
- Publisher
  NTS出版
- Data Source
  KAKENHI-PROJECT-20700126
[Book] Employing delay and probability discounting frameworks for a neuroeconomic understanding of gambling behavior. In M. J. Esposito, editor, Psychology of Gambling2008
- Author(s)
  Taiki Takahashi, Takaki Makino, Yu Ohmura, and Hiroki Fukui
- Publisher
  Nova Science
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] 実用化する強化学習技術2014
- Author(s)
  牧野貴樹
- Journal Title
  
  生産研究
  
  Volume: 66
- Data Source
  KAKENHI-PROJECT-25730128
[Journal Article] パネルティスカッション: 強化学習 @ 2025 A.D. - 10年後の強化学習が目指すもの2013
- Author(s)
  牧野貴樹, 澁谷長史, 白川真一
- Journal Title
  
  計測と制御
  
  Volume: 52 Pages: 1136-1143
- Data Source
  KAKENHI-PROJECT-25730128
[Journal Article] 自然言語処理における逆強化学習・模倣学習の適用2013
- Author(s)
  坪井祐太, 牧野貴樹
- Journal Title
  
  計測と制御
  
  Volume: 52 Pages: 922-927
- Data Source
  KAKENHI-PROJECT-25730128
[Journal Article] 部分観測環境のモデルパラメータに対する徒弟学習2012
- Author(s)
  牧野貴樹, 竹内誉羽
- Journal Title
  
  電子情報通信学会技術報告(IBISML2011-94)
  
  Volume: 111(480) Pages: 49-54
- NAID
  110009545975
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] 部分観測環境のモデルパラメータに対する徒弟学習2012
- Author(s)
  牧野貴樹, 竹内誉羽
- Journal Title
  
  信学技報
  
  Volume: Vol.111, No.480 Pages: 49-54
- NAID
  110009545975
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] Apprenticeship learning for model parameters of partially observable environments2012
- Author(s)
  Takaki Makino and Johane Takeuchi
- Journal Title
  
  To be appeared in ICML '12: Proceedings of the 29th Annual international conference on machine learning
- NAID
  110009545975
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] 強化学習(私のブックマーク)2011
- Author(s)
  牧野貴樹
- Journal Title
  
  人工知能学会誌
  
  Volume: Vol.26, No.3 Pages: 301-303
- NAID
  110008662160
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] ノンパラメトリックベイズに基づく統計的機械学習2010
- Author(s)
  牧野貴樹
- Journal Title
  
  電子情報通信学会技術研究報告IBISML2010-14
  
  Volume: 110(76) Pages: 87-94
- NAID
  110008096185
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] 利他的行動と再帰的他者推定2010
- Author(s)
  牧野貴樹, 滝久雄, 合原一幸
- Journal Title
  
  生産研究
  
  Volume: Vol.62, No.3 Pages: 259-265
- NAID
  130000342806
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] コミュニケーションの自己組織化2009
- Author(s)
  牧野貴樹
- Journal Title
  
  自己組織化ハンドブック(NTS出版)
  
  Pages: 438-443
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] Proto-predictive representation of states with simple recurrent temporal-difference networks2009
- Author(s)
  牧野貴樹
- Journal Title
  
  Proceedings of the 26th Annual international conference on machine learning 26
  
  Pages: 697-704
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] Cultural neuroeconomics of intertemporal choice2009
- Author(s)
  Taiki Takahashi, Tarik Hadzibeganovic, Sergio A. Cannas, Takaki Makino, Hiroki Fukui, and Shinobu Kitayama
- Journal Title
  
  Neuroendocrinology Letters
  
  Volume: Vol.30, No.2 Pages: 185-191
- NAID
  130004959898
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] Proto-Predictive Representation of States with Simple Recurrent Temporal-Difference Networks2009
- Author(s)
  Takaki Makino
- Journal Title
  
  Proceedings of the 26th International Conference of Machine Learning (ICML 2009) (印刷中)(掲載確定)
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] Proto-predictive representation of states with simple recurrent temporal-difference networks2009
- Author(s)
  Takaki Makino
- Journal Title
  
  In Leon Bottou and Michael Littman, editors, ICML '09 : Proceedings of the 26th Annual international conference on machine learning
  
  Volume: vol.26 Pages: 697-704
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] On-line Discovery of Temporal-Difference Networks2008
- Author(s)
  Takaki Makino and Toshihisa Takegi
- Journal Title
  
  Proceedings of the 25th International Conference of Machine Learning (ICML 2008)
  
  Pages: 632-639
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Journal Article] On-line discovery of temporal-difference networks2008
- Author(s)
  Takaki Makino and Toshihisa Takagi
- Journal Title
  
  In Andrew McCallum and Sam Roweis, editors, ICML '08 : Proceedings of the 25th Annual International Conference on Machine Learning
  
  Volume: vol.25 Pages: 632-639
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-20700126
[Patent] 画像再構成装置及びプログラム2011
- Inventor(s)
  小塚淳、牧野貴樹、水谷治央
- Industrial Property Rights Holder
  東京大学
- Filing Date
  2011-06-22
- Data Source
  KAKENHI-PROJECT-20200001
[Patent] 画像再構成装置及びプログラム2011
- Inventor(s)
  小塚淳、牧野貴樹、水谷治央
- Industrial Property Rights Holder
  東京大学
- Industrial Property Number
  2011-138833
- Filing Date
  2011-06-22
- Data Source
  KAKENHI-PROJECT-20200001
[Presentation] 機械学習の数学的側面2014
- Author(s)
  牧野貴樹
- Organizer
  ミニワークショップ「機械学習×力学系」
- Place of Presentation
  東京大学生産技術研究所
- Invited
- Data Source
  KAKENHI-PROJECT-25730128
[Presentation] 部分観測環境のパラメトリック記述に基づく高速モデルパラメータ逆強化学習プログラム2014
- Author(s)
  牧野貴樹, 城真範, 合原一幸
- Organizer
  人工知能学会全国大会
- Place of Presentation
  ひめぎんホール
- Data Source
  KAKENHI-PROJECT-25730128
[Presentation] 強化学習をベイズで理解する2014
- Author(s)
  牧野　貴樹
- Organizer
  神経科学と統計科学の対話４
- Place of Presentation
  統計数理研究所(立川市)
- Invited
- Data Source
  KAKENHI-PROJECT-25730128
[Presentation] Estimation of POMDP Parameters by Apprenticeship Learning2014
- Author(s)
  Takaki Makino
- Organizer
  Workshop on MDP/POMDP Applications to Medical Data
- Place of Presentation
  東京大学大学院情報理工学研究科 I-REF棟
- Invited
- Data Source
  KAKENHI-PROJECT-25730128
[Presentation] 部分観測環境のモデルパラメータに対する徒弟学習2012
- Author(s)
  牧野貴樹, 竹内誉羽
- Organizer
  電子情報通信学会情報論的学習理論と機械学習研究会
- Place of Presentation
  統計数理研究所
- Year and Date
  2012-03-12
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Learning model parameters of partially observable markov decision process from demonstration2012
- Author(s)
  Takaki Makino and Johane Takeuchi
- Organizer
  In Proc. Of the 2nd International Symposium on Innovative Mathematical Modeling
- Place of Presentation
  東京
- Year and Date
  2012-05-13
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Hierarchical Nested Infinite Hidden Markov Models2012
- Author(s)
  Takaki Makino
- Organizer
  Bayesian Inference and Stochastic Computation 2012 workshop
- Place of Presentation
  立川市
- Year and Date
  2012-06-22
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] べイズ推定に基づくX線CT再構成でのビームハードニング低減2011
- Author(s)
  牧野貴樹、水谷治央、小塚淳、佐藤一誠
- Organizer
  情報論的学習理論 (IBIS2011)
- Place of Presentation
  奈良
- Data Source
  KAKENHI-PROJECT-20200001
[Presentation] 隠れマルコフモデルのノンパラメトリックベイズ推定とMCMC法2010
- Author(s)
  牧野貴樹
- Organizer
  研究会『マルコフ連鎖モンテカルロ法とその周辺』
- Place of Presentation
  統計数理研究所(立川市)
- Year and Date
  2010-02-21
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] ノンパラメトリックベイズに基づく統計的機械学習2010
- Author(s)
  牧野貴樹
- Organizer
  電子情報通信学会技術研究報告IBISML2010-14,電子情報通信学会
- Place of Presentation
  東京
- Year and Date
  2010-06-15
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Slice sampling for chinese restaurant process2010
- Author(s)
  Takaki Makino
- Organizer
  In Proc. Of the 2nd Asian Conference on Machine Learning (ACML 2010)
- Place of Presentation
  Tokyo
- Year and Date
  2010-11-08
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] ノンパラメトリックベイズに基づく統計的機械学習2010
- Author(s)
  牧野貴樹
- Organizer
  電子情報通信学会情報論的学習理論と機械学習研究会
- Place of Presentation
  東京大学武田ホール
- Year and Date
  2010-06-15
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] 階層状態無限隠れマルコフモデル2009
- Author(s)
  牧野貴樹
- Organizer
  情報論的学習理論(IBIS)2009
- Place of Presentation
  九州大学(福岡市)
- Year and Date
  2009-10-19
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Conditional simultaneous draws from hierarchical chinese restaurant processes2009
- Author(s)
  Takaki Makino, Shunsuke Takei, Daichi Mochihashi, Issei Sato, Toshihisa Takagi
- Organizer
  Nonparametric Bayes Workshop at NIPS 2009(NPBayes 2009)
- Place of Presentation
  Whistler, BC, Canada
- Year and Date
  2009-12-11
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] ベイズ確率文脈自由文法のための高速構文木サンプリング法2009
- Author(s)
  武井俊祐, 牧野貴樹, 高木利久
- Organizer
  情報論的学習理論(IBIS)2009
- Place of Presentation
  九州大学(福岡市)
- Year and Date
  2009-10-19
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Probabilistic discounting for modeling behaviors in Iowa gambling task2009
- Author(s)
  Takaki Makino, Taiki Takahashi, Hirofumi Nishinaka, and Hiroki Fukui
- Organizer
  In Proceedings of Multi-disciplinary Symposium on Reinforcement Learning (MSRL2009)
- Place of Presentation
  Montreal, Canada
- Year and Date
  2009-06-18
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] 階層状態無限隠れマルコフモデル2009
- Author(s)
  牧野貴樹
- Organizer
  情報論的学習理論 (IBIS2009)ポスター発表
- Place of Presentation
  福岡市
- Year and Date
  2009-10-20
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Simple Recurrent Temporal-Difference Networks2008
- Author(s)
  Takaki Makino
- Organizer
  第11回情報論的学習論ワークショップ
- Place of Presentation
  仙台国際センター
- Year and Date
  2008-10-29
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] POMDP環境中でのTD-networkの自動獲得 : 単純再帰構造による拡張2008
- Author(s)
  牧野貴樹
- Organizer
  第22回人工知能学会全国大会
- Place of Presentation
  旭川市
- Year and Date
  2008-06-13
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] 自己観測原理 : 他者認知の数理的枠組2008
- Author(s)
  牧野貴樹, 合原一幸
- Organizer
  第22回人工知能学会全国大会
- Place of Presentation
  旭川市
- Year and Date
  2008-06-13
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] Simple recurrent temporal-difference networks2008
- Author(s)
  Takaki Makino
- Organizer
  情報論的学習理論ワークショップ (IBIS2008)
- Place of Presentation
  仙台市
- Year and Date
  2008-10-29
- Data Source
  KAKENHI-PROJECT-20700126
[Presentation] POのP環境中でのTD-Networkの自動獲得 : 単純再帰構造による拡張2008
- Author(s)
  牧野貴樹
- Organizer
  人工知能学会第22回全国大会
- Place of Presentation
  ときわ市民ホール(旭川市)
- Year and Date
  2008-10-29
- Data Source
  KAKENHI-PROJECT-20700126

1. MIZUTANI Haruo (40444103)

# of Collaborated Projects: 1 results

# of Collaborated Products: 1 results

MAKINO Takaki 牧野 貴樹

Research Projects

Research Products

Co-Researchers

環境モデル徒弟学習の抜本的高速化技術の開発と実用的対話システムのプロトタイプ構築Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Connectome Project X: X-ray microscopy revealing neuronal wiring diagram

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Computational Theory of Inductive Reinforcement Learning-Bayesian Inference on Environment Search and Inductive ReconstructionPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

[Book] コミュニケーションの自己組織化. 国武豊喜 (監修), 自己組織化ハンドブック2009

Author(s)

Publisher

Data Source

[Book] Employing delay and probability discounting frameworks for a neuroeconomic understanding of gambling behavior. In M. J. Esposito, editor, Psychology of Gambling2008

Author(s)

Publisher

Data Source

[Journal Article] 実用化する強化学習技術2014

Author(s)

Journal Title

Data Source

[Journal Article] パネルティスカッション: 強化学習 @ 2025 A.D. - 10年後の強化学習が目指すもの2013

Author(s)

Journal Title

Data Source

[Journal Article] 自然言語処理における逆強化学習・模倣学習の適用2013

Author(s)

Journal Title

Data Source

[Journal Article] 部分観測環境のモデルパラメータに対する徒弟学習2012

Author(s)

Journal Title

NAID

Data Source

[Journal Article] 部分観測環境のモデルパラメータに対する徒弟学習2012

Author(s)

Journal Title

NAID

Data Source

[Journal Article] Apprenticeship learning for model parameters of partially observable environments2012

Author(s)

Journal Title

NAID

Data Source

[Journal Article] 強化学習(私のブックマーク)2011

Author(s)

Journal Title

NAID

Data Source

[Journal Article] ノンパラメトリックベイズに基づく統計的機械学習2010

Author(s)

Journal Title

NAID

Data Source

[Journal Article] 利他的行動と再帰的他者推定2010

Author(s)

Journal Title

NAID

Data Source

[Journal Article] コミュニケーションの自己組織化2009

Author(s)

Journal Title

Data Source

[Journal Article] Proto-predictive representation of states with simple recurrent temporal-difference networks2009

Author(s)

Journal Title

Data Source

MAKINO Takaki 牧野貴樹