研究者詳細 - 上野　史

論文 - 上野　史

分割表示 63 件中 21 - 40 件目／全件表示 >>

Table-structure Recognition Method Consisting of Plural Neural Network Modules.

Hiroyuki Aoyagi, Teruhito Kanazawa, Atsuhiro Takasu, Fumito Uwano, Manabu Ohta

Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods(ICPRAM) 542 - 549 2022年

複雑ネットワークに基づく多次元意見共有モデル上の誤報伝搬防止査読

上野史, 北島瑛貴, 高玉圭樹

人工知能学会論文誌 36 ( 6 ) B-KB2_1 - 12 2021年11月

A Cooperative Learning Method for Multi-Agent System with Different Input Resolutions. 査読

Fumito Uwano

4th International Symposium on Agents, Multi-Agent Systems and Robotics(ISAMSR) 84 - 90 2021年9月

Directionality Reinforcement Learning to Operate Multi-Agent System without Communication. 査読

Fumito Uwano, Keiki Takadama

CoRR abs/2110.05773 2021年

多次元意見共有モデル上のシグモイド関数に基づく誤報防止アルゴリズム査読

上野史, 北島瑛貴, 髙玉圭樹

人工知能学会論文誌 36 ( 6 ) 2021年

How to Emote for Consensus Building in Virtual Communication. 査読

Yoshimiki Maekawa, Fumito Uwano, Eiki Kitajima, Keiki Takadama

Human Interface and the Management of Information. Interacting with Information - Thematic Area 194 - 205 2020年7月

Reward Value-Based Goal Selection for Agents’ Cooperative Route Learning Without Communication in Reward and Goal Dynamism 査読

上野史, 髙玉圭樹

SN Computer Science 1 ( 3 ) 182 - 182 2020年5月

Theoretical learning goal selection for non-communicative multi-agent cooperation

Fumito Uwano, Keiki Takadama

IEEJ Transactions on Electronics, Information and Systems 140 ( 1 ) 75 - 84 2020年

記述言語：日本語掲載種別：研究論文（学術雑誌）出版者・発行元：Institute of Electrical Engineers of Japan

This paper extended PMRL as the non-communicative and theoretical method for two agents, and proposed PLA as the method to be able to force agents to learn cooperative behavior for any number of agents. In addition, this paper adds the theoretic explanation for PLA that all agents achieve all purposes without spending the largest times. Concretely PLA forces each agent to avoid the more difficult purposes requiring many time to be reached by limiting the purpose which it can achieve, and it forces the agents to learn cooperative policy as achieving the appropriate purpose among the limited purposes. The experimental results in this paper derive that (1) PLA enables the agents to learn cooperative policy in the two grid world problems for three and five agents, and (2) PLA can force all agents to achieve all purposes in the problems with the minimum time.

DOI： 10.1541/ieejeiss.140.75

Scopus

researchmap

How to Design Adaptable Agents to Obtain a Consensus with Omoiyari. 査読

Yoshimiki Maekawa, Fumito Uwano, Eiki Kitajima, Keiki Takadama

Human Interface and the Management of Information. Visual Information and Knowledge Management - Thematic Area 462 - 475 2019年7月

How to Select Appropriate Craters to Estimate Location Accurately in Comprehensive Situations for SLIM Project 査読

上野史, 辰巳嵩豊, 村田暁紀, 髙玉圭樹, 鎌田弘之, 石田貴行, 福田盛介, 澤井秀次郎, 坂井真一郎

Proceedings of the 32nd International Symposium on Space Technology and Science (ISTS) & 9th Nano-Satellite Symposium (NSAT) 2019年6月

Bat Algorithm with Dynamic Niche Radius for Multimodal Optimization 査読

岩瀬拓哉, 高野諒, 上野史, 佐藤寛之, 高玉圭樹

Proceedings of the 3rd International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI 2019) 2019年3月

Maximum Entropy Inverse Reinforcement Learning with Incomplete Experts 査読

長谷川智, 上野史, 髙玉圭樹

Proceedings of the 24th International Symposium on Artificial Life and Robotics 2019年1月

Utilizing Observed Information for No-Communication Multi-agent Reinforcement Learning toward Cooperation in Dynamic Environment 査読

上野史, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 2019年

目的制限に基づく通信なしマルチエージェント協調行動学習とその効果の証明査読

上野史, 髙玉圭樹

電気学会論文誌C 140 ( 1 ) 2019年

Niche Radius Adaptation in Bat Algorithm for Locating Multiple Optima in Multimodal Functions. 査読

Takuya Iwase, Ryo Takano, Fumito Uwano, Hiroyuki Sato, Keiki Takadama

IEEE Congress on Evolutionary Computation(CEC) 800 - 807 2019年

Novelty Search-based Bat Algorithm: Adjusting Distance among Solutions for Multimodal Optimization 査読

岩瀬拓哉, 髙野諒, 上野史, 佐藤寛之, 髙玉圭樹

Proceedings of the 22nd Asia Pacific Symposium on Intelligent and Evolutionary Systems 2018年12月

Strategy for Learning Cooperative Behavior with Local Information for Multi-agent Systems 査読

上野史, 髙玉圭樹

Proceedings of The 21st International Conference on Principles and Practice of Multi-Agent Systems 663 - 670 2018年10月

Multiple swarm intelligence methods based on multiple population with sharing best solution for drastic environmental change. 査読

Yuta Umenai, Fumito Uwano, Hiroyuki Sato, Keiki Takadama

Proceedings of the Genetic and Evolutionary Computation Conference Companion 97 - 98 2018年7月

Weighted Opinion Sharing Model for Cutting Link and Changing Information among Agents as Dynamic Environment 査読

上野史, 齋藤嶺, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 11 ( 4 ) 331 - 340 2018年7月

Multi-Agent Cooperation Based on Reinforcement Learning with Internal Reward in Maze Problem 査読

上野史, 建部尚樹, 田島友祐, 中田雅也, ティム・コバックス, 髙玉圭樹

SICE Journal of Control, Measurement, and System Integration 11 ( 4 ) 321 - 330 2018年7月

　前のページ - 次のページ　

<上野 史>

論文 - 上野 史

<上野　史>

論文 - 上野　史