JP2019159888A5 - - Google Patents

Download PDF

Info

Publication number
JP2019159888A5
JP2019159888A5 JP2018046510A JP2018046510A JP2019159888A5 JP 2019159888 A5 JP2019159888 A5 JP 2019159888A5 JP 2018046510 A JP2018046510 A JP 2018046510A JP 2018046510 A JP2018046510 A JP 2018046510A JP 2019159888 A5 JP2019159888 A5 JP 2019159888A5
Authority
JP
Japan
Prior art keywords
evaluation
reward
value
machine learning
scale
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.)
Granted
Application number
JP2018046510A
Other languages
English (en)
Japanese (ja)
Other versions
JP2019159888A (ja
JP6902487B2 (ja
Filing date
Publication date
Application filed filed Critical
Priority to JP2018046510A priority Critical patent/JP6902487B2/ja
Priority claimed from JP2018046510A external-priority patent/JP6902487B2/ja
Publication of JP2019159888A publication Critical patent/JP2019159888A/ja
Publication of JP2019159888A5 publication Critical patent/JP2019159888A5/ja
Application granted granted Critical
Publication of JP6902487B2 publication Critical patent/JP6902487B2/ja
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

JP2018046510A 2018-03-14 2018-03-14 機械学習システム Expired - Fee Related JP6902487B2 (ja)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2018046510A JP6902487B2 (ja) 2018-03-14 2018-03-14 機械学習システム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2018046510A JP6902487B2 (ja) 2018-03-14 2018-03-14 機械学習システム

Publications (3)

Publication Number Publication Date
JP2019159888A JP2019159888A (ja) 2019-09-19
JP2019159888A5 true JP2019159888A5 (enrdf_load_stackoverflow) 2020-04-09
JP6902487B2 JP6902487B2 (ja) 2021-07-14

Family

ID=67996270

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2018046510A Expired - Fee Related JP6902487B2 (ja) 2018-03-14 2018-03-14 機械学習システム

Country Status (1)

Country Link
JP (1) JP6902487B2 (enrdf_load_stackoverflow)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110328668B (zh) * 2019-07-27 2022-03-22 南京理工大学 基于速度平滑确定性策略梯度的机械臂路径规划方法
JP7436688B2 (ja) * 2020-02-07 2024-02-22 ディープマインド テクノロジーズ リミテッド 目的別行動価値関数を使用する多目的強化学習
CN112853560B (zh) * 2020-12-31 2021-11-23 盐城师范学院 一种基于环锭纺纱线质量的全局工序共享控制系统及方法
CN112953844B (zh) * 2021-03-02 2023-04-28 中国农业银行股份有限公司 一种网络流量优化方法及装置
CN115284285B (zh) * 2022-07-29 2025-01-14 腾讯科技(深圳)有限公司 目标对象控制方法和装置、计算设备、存储介质
CN116976442A (zh) * 2023-06-04 2023-10-31 西北工业大学 一种基于me-ddpg的无人机多对一追捕博弈方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3086206B2 (ja) * 1998-07-17 2000-09-11 科学技術振興事業団 エージェント学習装置
JP5330138B2 (ja) * 2008-11-04 2013-10-30 本田技研工業株式会社 強化学習システム

Similar Documents

Publication Publication Date Title
JP2019159888A5 (enrdf_load_stackoverflow)
JP7510637B2 (ja) 汎用学習済モデルの生成方法
JP2021507323A5 (enrdf_load_stackoverflow)
Ostertagová et al. The simple exponential smoothing model
JP2019503258A5 (enrdf_load_stackoverflow)
JP2015210750A5 (enrdf_load_stackoverflow)
WO2017091629A1 (en) Reinforcement learning using confidence scores
JP2017191607A5 (enrdf_load_stackoverflow)
JP2019219741A5 (enrdf_load_stackoverflow)
JPWO2016152053A1 (ja) 精度推定モデル生成システムおよび精度推定システム
JP2017519282A5 (enrdf_load_stackoverflow)
US11762679B2 (en) Information processing device, information processing method, and non-transitory computer-readable storage medium
JP2015109891A5 (enrdf_load_stackoverflow)
JP2014517602A5 (enrdf_load_stackoverflow)
SG10201803377PA (en) Ametropia treatment tracking methods and system
JP2013190427A5 (enrdf_load_stackoverflow)
GB2579789A (en) Runtime parameter selection in simulations
JP2017504087A5 (enrdf_load_stackoverflow)
JPWO2021064787A5 (enrdf_load_stackoverflow)
JP2020112967A5 (enrdf_load_stackoverflow)
JP2019060642A5 (enrdf_load_stackoverflow)
US10635078B2 (en) Simulation system, simulation method, and simulation program
Pant et al. Application of a multi-objective particle article swarm optimization technique to solve reliability optimization problem
JP2019128904A (ja) 予測システム、シミュレーションシステム、方法およびプログラム
KR20170023098A (ko) 타겟 시스템 제어