WO2002063402A1 - Appareil, procede et programme d'apprentissage pour agent - Google Patents

Appareil, procede et programme d'apprentissage pour agent Download PDF

Info

Publication number
WO2002063402A1
WO2002063402A1 PCT/JP2002/000878 JP0200878W WO02063402A1 WO 2002063402 A1 WO2002063402 A1 WO 2002063402A1 JP 0200878 W JP0200878 W JP 0200878W WO 02063402 A1 WO02063402 A1 WO 02063402A1
Authority
WO
WIPO (PCT)
Prior art keywords
action
sense input
action output
column
output
Prior art date
Application number
PCT/JP2002/000878
Other languages
English (en)
French (fr)
Inventor
Takamasa Koshizen
Hiroshi Tsujino
Original Assignee
Honda Giken Kogyo Kabushiki Kaisha
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Honda Giken Kogyo Kabushiki Kaisha filed Critical Honda Giken Kogyo Kabushiki Kaisha
Priority to US10/468,316 priority Critical patent/US20060155660A1/en
Priority to EP02710486A priority patent/EP1359481A4/en
Priority to JP2002563083A priority patent/JP4028384B2/ja
Publication of WO2002063402A1 publication Critical patent/WO2002063402A1/ja

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
PCT/JP2002/000878 2001-02-05 2002-02-04 Appareil, procede et programme d'apprentissage pour agent WO2002063402A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US10/468,316 US20060155660A1 (en) 2001-02-05 2002-02-04 Agent learning apparatus, method and program
EP02710486A EP1359481A4 (en) 2001-02-05 2002-02-04 AGENT LEARNING DEVICE, METHOD AND PROGRAM
JP2002563083A JP4028384B2 (ja) 2001-02-05 2002-02-04 エージェント学習装置、方法、プログラム

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
JP2001-028759 2001-02-05
JP2001028758 2001-02-05
JP2001-028758 2001-02-05
JP2001028759 2001-02-05

Publications (1)

Publication Number Publication Date
WO2002063402A1 true WO2002063402A1 (fr) 2002-08-15

Family

ID=26608946

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2002/000878 WO2002063402A1 (fr) 2001-02-05 2002-02-04 Appareil, procede et programme d'apprentissage pour agent

Country Status (4)

Country Link
US (1) US20060155660A1 (ja)
EP (1) EP1359481A4 (ja)
JP (1) JP4028384B2 (ja)
WO (1) WO2002063402A1 (ja)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010073200A (ja) * 2008-09-18 2010-04-02 Honda Motor Co Ltd 学習システム及び学習方法
JP2017199074A (ja) * 2016-04-25 2017-11-02 ファナック株式会社 製品の異常に関連する変数の判定値を設定する生産システム

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7152051B1 (en) 2002-09-30 2006-12-19 Michael Lamport Commons Intelligent control with hierarchical stacked neural networks
US20060184462A1 (en) 2004-12-10 2006-08-17 Hawkins Jeffrey C Methods, architecture, and apparatus for implementing machine intelligence and hierarchical memory systems
US20070192267A1 (en) * 2006-02-10 2007-08-16 Numenta, Inc. Architecture of a hierarchical temporal memory based system
US8732098B2 (en) 2006-02-10 2014-05-20 Numenta, Inc. Hierarchical temporal memory (HTM) system deployed as web service
FI20070159A0 (fi) * 2007-02-23 2007-02-23 Teknillinen Korkeakoulu Menetelmä informaation integrointiin, valintaan ja esityksen oppimiseen
US9015093B1 (en) 2010-10-26 2015-04-21 Michael Lamport Commons Intelligent control with hierarchical stacked neural networks
US8775341B1 (en) 2010-10-26 2014-07-08 Michael Lamport Commons Intelligent control with hierarchical stacked neural networks
US10152037B2 (en) 2013-07-09 2018-12-11 Ford Global Technologies, Llc System and method for feedback error learning in non-linear systems
JP6457369B2 (ja) * 2015-09-30 2019-01-23 ファナック株式会社 パラメータを自動調整する機能を有する機械学習装置及び電動機制御装置
US10839302B2 (en) 2015-11-24 2020-11-17 The Research Foundation For The State University Of New York Approximate value iteration with complex returns by bounding
JP6203808B2 (ja) * 2015-11-27 2017-09-27 ファナック株式会社 ファンモータの清掃間隔を学習する機械学習器、モータ制御システムおよび機械学習方法
US10817801B2 (en) 2016-07-25 2020-10-27 General Electric Company System and method for process modeling and control using disturbance rejection models
CA2982930A1 (en) 2017-10-18 2019-04-18 Kari Saarenvirta System and method for selecting promotional products for retail
GB2567900A (en) 2017-10-31 2019-05-01 Babylon Partners Ltd A computer implemented determination method and system
US10621533B2 (en) 2018-01-16 2020-04-14 Daisy Intelligence Corporation System and method for operating an enterprise on an autonomous basis
US11281208B2 (en) * 2018-03-02 2022-03-22 Carnegie Mellon University Efficient teleoperation of mobile robots via online adaptation
US11887138B2 (en) 2020-03-03 2024-01-30 Daisy Intelligence Corporation System and method for retail price optimization
JP6950117B1 (ja) * 2020-04-30 2021-10-13 楽天グループ株式会社 学習装置、情報処理装置、及び学習済の制御モデル
US11783338B2 (en) 2021-01-22 2023-10-10 Daisy Intelligence Corporation Systems and methods for outlier detection of transactions

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02306364A (ja) * 1989-05-22 1990-12-19 Nkk Corp 高炉の操業支援方法
JPH02308301A (ja) * 1989-05-24 1990-12-21 Hitachi Ltd プラント運転支援装置
JPH03260704A (ja) * 1990-03-09 1991-11-20 Kobe Steel Ltd アクション決定装置
JPH04360238A (ja) * 1991-06-06 1992-12-14 Omron Corp 学習機能付き推論装置
JPH05204650A (ja) * 1992-01-27 1993-08-13 Omron Corp 知識学習装置
JPH05265511A (ja) * 1992-03-19 1993-10-15 Hitachi Ltd 制御システム
JP2000035956A (ja) * 1998-07-17 2000-02-02 Japan Science & Technology Corp エージェント学習装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02306364A (ja) * 1989-05-22 1990-12-19 Nkk Corp 高炉の操業支援方法
JPH02308301A (ja) * 1989-05-24 1990-12-21 Hitachi Ltd プラント運転支援装置
JPH03260704A (ja) * 1990-03-09 1991-11-20 Kobe Steel Ltd アクション決定装置
JPH04360238A (ja) * 1991-06-06 1992-12-14 Omron Corp 学習機能付き推論装置
JPH05204650A (ja) * 1992-01-27 1993-08-13 Omron Corp 知識学習装置
JPH05265511A (ja) * 1992-03-19 1993-10-15 Hitachi Ltd 制御システム
JP2000035956A (ja) * 1998-07-17 2000-02-02 Japan Science & Technology Corp エージェント学習装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP1359481A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010073200A (ja) * 2008-09-18 2010-04-02 Honda Motor Co Ltd 学習システム及び学習方法
JP2017199074A (ja) * 2016-04-25 2017-11-02 ファナック株式会社 製品の異常に関連する変数の判定値を設定する生産システム
US10782664B2 (en) 2016-04-25 2020-09-22 Fanuc Corporation Production system that sets determination value of variable relating to abnormality of product

Also Published As

Publication number Publication date
EP1359481A1 (en) 2003-11-05
EP1359481A4 (en) 2006-04-12
JP4028384B2 (ja) 2007-12-26
JPWO2002063402A1 (ja) 2004-06-10
US20060155660A1 (en) 2006-07-13

Similar Documents

Publication Publication Date Title
WO2002063402A1 (fr) Appareil, procede et programme d'apprentissage pour agent
Prasad et al. Nonlinear system identification and model reduction using artificial neural networks
WO2002042720A3 (en) Inferential signal generator for instrumented equipment and processes
WO2004086208A3 (en) Apparatus and method for generating behaviour in an object
WO2006132943A3 (en) Method and apparatus for controlling a component by feed-forward closed-loop controller state modification
WO2007047868A3 (en) System, method, and computer program for early event detection
CA2417194A1 (en) Parameterized graphs with conditional components
WO2002031608A3 (en) Plc executive with integrated web server
WO2006026021A3 (en) Device orientation based input signal generation
JP2010534881A5 (ja)
WO2004059411A8 (en) System and method for testing a control system of a marine vessel
WO2005050698A3 (en) System and method for on-tool semiconductor simulation
WO2004097631A3 (en) Architecture for generating intermediate representations for program code conversion
CA2249822A1 (en) Off-line teaching method and apparatus
KR20180103671A (ko) 언어 모델을 압축하기 위한 전자 장치, 추천 워드를 제공하기 위한 전자 장치 및 그 동작 방법들
WO2005044622A3 (en) Method and apparatus for loss of control inhibitor systems
US20060184467A1 (en) Sensor and sensor program storage medium
WO2004104749A3 (en) Method for generating a baked component that approximates the behavior of animation models
WO2006090546A3 (en) Input device for a computer and environmental control system using the same
WO2001071531A3 (en) Method of analyzing chemical processes
JP2008242572A (ja) 制御処理シミュレーション装置
JP2007233930A (ja) 分散制御システム用シミュレータ
WO2022167870A3 (en) Prediction of pipeline column separations
Der Selforganized robot behavior from the principle of homeokinesis
WO2002067064A3 (de) Verfahren und vorrichtung zur durchführung der funktionalitätsprüfung sowie funktionalitätsprüfung eines technischen aggregates

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): JP US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
WWE Wipo information: entry into national phase

Ref document number: 2002563083

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 2002710486

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 2002710486

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2006155660

Country of ref document: US

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 10468316

Country of ref document: US

WWP Wipo information: published in national office

Ref document number: 10468316

Country of ref document: US

WWW Wipo information: withdrawn in national office

Ref document number: 2002710486

Country of ref document: EP