JP6981539B2 - モデル推定システム、モデル推定方法およびモデル推定プログラム - Google Patents
モデル推定システム、モデル推定方法およびモデル推定プログラム Download PDFInfo
- Publication number
- JP6981539B2 JP6981539B2 JP2020508787A JP2020508787A JP6981539B2 JP 6981539 B2 JP6981539 B2 JP 6981539B2 JP 2020508787 A JP2020508787 A JP 2020508787A JP 2020508787 A JP2020508787 A JP 2020508787A JP 6981539 B2 JP6981539 B2 JP 6981539B2
- Authority
- JP
- Japan
- Prior art keywords
- model
- objective function
- behavior
- data
- behavior data
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 15
- 230000006870 function Effects 0.000 claims description 84
- 230000006399 behavior Effects 0.000 claims description 80
- 230000002787 reinforcement Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000010365 information processing Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000001133 acceleration Effects 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/043—Distributed expert systems; Blackboards
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/045—Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
Description
101 データ入力装置
102 構造設定部
103 データ分割部
104 モデル学習部
105 モデル推定結果出力装置
Claims (10)
- 環境の状態と当該環境の元で行われる行動とを対応付けたデータである行動データ、前記行動データに基づいて前記行動に応じた状態を予測する予測モデル、および、前記状態と行動とを合わせて評価する目的関数の説明変数とを入力する入力部と、
階層混合エキスパートモデルの最下層のノードに前記目的関数が配される分岐構造を設定する構造設定部と、
前記分岐構造に従って分割される前記行動データに対して前記予測モデルを適用して予測される状態に基づいて、前記階層混合エキスパートモデルのノードにおける分岐条件および前記説明変数を含む前記目的関数を学習する学習部とを備えた
ことを特徴とするモデル推定システム。 - 学習部は、EMアルゴリズムおよび逆強化学習により、分岐条件および目的関数を学習する
請求項1記載のモデル推定システム。 - 学習部は、最大エントロピー逆強化学習、ベイジアン逆強化学習または最大尤度逆強化学習により目的関数を学習する
請求項1または請求項2記載のモデル推定システム。 - 学習部は、分岐条件および目的関数が学習された階層混合エキスパートモデルに行動データを適用した結果と当該行動データとの乖離度合いを評価し、前記乖離度合いが所定の閾値以内になるまで学習を繰り返す
請求項1から請求項3のうちのいずれか1項に記載のモデル推定システム。 - 学習部は、階層混合エキスパートモデルの最下層のノードに対応させて行動データを分割し、予測モデルおよび分割された行動データを用いて、分割された行動データごとに目的関数および分岐条件を学習する
請求項1から請求項4のうちのいずれか1項に記載のモデル推定システム。 - 分岐条件は、説明変数を用いた条件を含む
請求項1から請求項5のうちのいずれか1項に記載のモデル推定システム。 - 入力部は、店舗における発注履歴または価格設定履歴を行動データとして入力し、
学習部は、価格の最適化に用いられる目的関数を学習する
請求項1から請求項6のうちのいずれか1項に記載のモデル推定システム。 - 入力部は、ドライバの走行履歴を行動データとして入力し、
学習部は、車両運転の最適化に用いられる目的関数を学習する
請求項1から請求項6のうちのいずれか1項に記載のモデル推定システム。 - 環境の状態と当該環境の元で行われる行動とを対応付けたデータである行動データ、前記行動データに基づいて前記行動に応じた状態を予測する予測モデル、および、前記状態と行動とを合わせて評価する目的関数の説明変数とを入力し、
階層混合エキスパートモデルの最下層のノードに前記目的関数が配される分岐構造を設定し、
前記分岐構造に従って分割される前記行動データに対して前記予測モデルを適用して予測される状態に基づいて、前記階層混合エキスパートモデルのノードにおける分岐条件および前記説明変数を含む前記目的関数を学習する
ことを特徴とするモデル推定方法。 - コンピュータに、
環境の状態と当該環境の元で行われる行動とを対応付けたデータである行動データ、前記行動データに基づいて前記行動に応じた状態を予測する予測モデル、および、前記状態と行動とを合わせて評価する目的関数の説明変数とを入力する入力処理、
階層混合エキスパートモデルの最下層のノードに前記目的関数が配される分岐構造を設定する構造設定処理、および、
前記分岐構造に従って分割される前記行動データに対して前記予測モデルを適用して予測される状態に基づいて、前記階層混合エキスパートモデルのノードにおける分岐条件および前記説明変数を含む前記目的関数を学習する学習処理
を実行させるためのモデル推定プログラム。
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2018/013589 WO2019186996A1 (ja) | 2018-03-30 | 2018-03-30 | モデル推定システム、モデル推定方法およびモデル推定プログラム |
Publications (2)
Publication Number | Publication Date |
---|---|
JPWO2019186996A1 JPWO2019186996A1 (ja) | 2021-03-11 |
JP6981539B2 true JP6981539B2 (ja) | 2021-12-15 |
Family
ID=68062622
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2020508787A Active JP6981539B2 (ja) | 2018-03-30 | 2018-03-30 | モデル推定システム、モデル推定方法およびモデル推定プログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US20210150388A1 (ja) |
JP (1) | JP6981539B2 (ja) |
WO (1) | WO2019186996A1 (ja) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11410558B2 (en) * | 2019-05-21 | 2022-08-09 | International Business Machines Corporation | Traffic control with reinforcement learning |
US20220390909A1 (en) * | 2019-11-14 | 2022-12-08 | Nec Corporation | Learning device, learning method, and learning program |
US20220318917A1 (en) * | 2019-12-25 | 2022-10-06 | Nec Corporation | Intention feature value extraction device, learning device, method, and program |
WO2021130915A1 (ja) * | 2019-12-25 | 2021-07-01 | 日本電気株式会社 | 学習装置、学習方法および学習プログラム |
CN113525400A (zh) * | 2021-06-21 | 2021-10-22 | 上汽通用五菱汽车股份有限公司 | 变道提醒方法、装置、车辆及可读存储介质 |
CN115952073B (zh) * | 2023-03-13 | 2023-06-13 | 广州市易鸿智能装备有限公司 | 工控机性能评估方法、装置、电子设备及存储介质 |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6671661B1 (en) * | 1999-05-19 | 2003-12-30 | Microsoft Corporation | Bayesian principal component analysis |
US7809704B2 (en) * | 2006-06-15 | 2010-10-05 | Microsoft Corporation | Combining spectral and probabilistic clustering |
US8538795B2 (en) * | 2007-02-12 | 2013-09-17 | Pricelock, Inc. | System and method of determining a retail commodity price within a geographic boundary |
US7953676B2 (en) * | 2007-08-20 | 2011-05-31 | Yahoo! Inc. | Predictive discrete latent factor models for large scale dyadic data |
JP2011118777A (ja) * | 2009-12-04 | 2011-06-16 | Sony Corp | 学習装置および学習方法、予測装置および予測方法、並びにプログラム |
JP2011252844A (ja) * | 2010-06-03 | 2011-12-15 | Sony Corp | データ処理装置、データ処理方法、およびプログラム |
US9047559B2 (en) * | 2011-07-22 | 2015-06-02 | Sas Institute Inc. | Computer-implemented systems and methods for testing large scale automatic forecast combinations |
US9043261B2 (en) * | 2012-05-31 | 2015-05-26 | Nec Corporation | Latent variable model estimation apparatus, and method |
JP6011788B2 (ja) * | 2012-09-03 | 2016-10-19 | マツダ株式会社 | 車両用制御装置 |
EP3171321A4 (en) * | 2014-07-14 | 2017-12-27 | Nec Corporation | Commercial message planning assistance system and sales prediction assistance system |
US10627813B2 (en) * | 2015-04-21 | 2020-04-21 | Panasonic Intellectual Property Management Co., Ltd. | Information processing system, information processing method, and program |
US20190026660A1 (en) * | 2016-02-03 | 2019-01-24 | Nec Corporation | Optimization system, optimization method, and recording medium |
CN108885722A (zh) * | 2016-03-25 | 2018-11-23 | 索尼公司 | 信息处理设备 |
US10902349B2 (en) * | 2016-06-21 | 2021-01-26 | Sri International | Systems and methods for machine learning using a trusted model |
JP6848230B2 (ja) * | 2016-07-01 | 2021-03-24 | 日本電気株式会社 | 処理装置、処理方法及びプログラム |
JP6827197B2 (ja) * | 2016-07-22 | 2021-02-10 | パナソニックIpマネジメント株式会社 | 情報推定システム及び情報推定方法 |
WO2018085643A1 (en) * | 2016-11-04 | 2018-05-11 | Google Llc | Mixture of experts neural networks |
US20190272465A1 (en) * | 2018-03-01 | 2019-09-05 | International Business Machines Corporation | Reward estimation via state prediction using expert demonstrations |
-
2018
- 2018-03-30 JP JP2020508787A patent/JP6981539B2/ja active Active
- 2018-03-30 US US17/043,783 patent/US20210150388A1/en active Pending
- 2018-03-30 WO PCT/JP2018/013589 patent/WO2019186996A1/ja active Application Filing
Also Published As
Publication number | Publication date |
---|---|
JPWO2019186996A1 (ja) | 2021-03-11 |
US20210150388A1 (en) | 2021-05-20 |
WO2019186996A1 (ja) | 2019-10-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6981539B2 (ja) | モデル推定システム、モデル推定方法およびモデル推定プログラム | |
Eom et al. | The traffic signal control problem for intersections: a review | |
Jin et al. | A group-based traffic signal control with adaptive learning ability | |
Daganzo et al. | A general model of demand-responsive transportation services: From taxi to ridesharing to dial-a-ride | |
Wiering et al. | Intelligent traffic light control | |
CN112400192B (zh) | 多模态深度交通信号控制的方法和系统 | |
de Oliveira et al. | Reinforcement Learning based Control of Traffic Lights in Non-stationary Environments: A Case Study in a Microscopic Simulator. | |
Prothmann et al. | Organic control of traffic lights | |
Sun et al. | Interpretable modelling of driving behaviors in interactive driving scenarios based on cumulative prospect theory | |
US20220036122A1 (en) | Information processing apparatus and system, and model adaptation method and non-transitory computer readable medium storing program | |
Lamouik et al. | Smart multi-agent traffic coordinator for autonomous vehicles at intersections | |
Miletić et al. | A review of reinforcement learning applications in adaptive traffic signal control | |
Liu et al. | A three-level game-theoretic decision-making framework for autonomous vehicles | |
Castro et al. | Biologically-inspired neural network for traffic signal control | |
Shamsi et al. | Reinforcement learning for traffic light control with emphasis on emergency vehicles | |
Sur | UCRLF: unified constrained reinforcement learning framework for phase-aware architectures for autonomous vehicle signaling and trajectory optimization | |
Sathyan et al. | Decentralized cooperative driving automation: a reinforcement learning framework using genetic fuzzy systems | |
Han et al. | Exploiting beneficial information sharing among autonomous vehicles | |
Abdelhameed et al. | A hybrid fuzzy-genetic controller for a multi-agent intersection control system | |
Valiente et al. | Learning-based social coordination to improve safety and robustness of cooperative autonomous vehicles in mixed traffic | |
Zhang et al. | A Bi-level Network-wide Cooperative Driving Approach Including Deep Reinforcement Learning-based Routing | |
Vidhate et al. | Exploring cooperative multi-agent reinforcement learning algorithm (cmrla) for intelligent traffic signal control | |
Jin et al. | Voluntary lane-change policy synthesis with control improvisation | |
Tomás et al. | An agent-based platform to evaluate V2X routing road traffic scenarios | |
Alms et al. | Reinforcement learning-based traffic control: Mitigating the adverse impacts of control transitions |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20200925 |
|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20200925 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20210803 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20211019 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20211101 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 6981539 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |