YAMAGUCHI Tomohiro

J-GLOBAL         Last updated: Jun 9, 2018 at 02:59
 
Avatar
Name
YAMAGUCHI Tomohiro
Affiliation
Nara National College of Technology
Section
Department of Information Engineering
Job title
Associate Professor
Degree
M. S. degree(Osaka University), Ph. D. degree(Osaka University)

Research Areas

 
 

Academic & Professional Experience

 
Apr 2007
 - 
Today
Professor, Nara National College of Technology
 
Apr 1998
 - 
Mar 2007
Assistant Professor, Nara National College of Technology
 
Oct 1990
 - 
Mar 1998
Reasearch Assistant, Graduate School of Engineering Science, Osaka University
 

Education

 
 
 - 
1990
Graduate School, Division of Engineering Science, Osaka University
 
Apr 1985
 - 
Mar 1987
Graduate School of Engineering Science, Osaka University
 
Apr 1980
 - 
Mar 1985
Osaka University
 
 
 - 
1985
Faculty of Engineering Science, Osaka University
 

Published Papers

 
Awareness based recommendation - Toward the Cooperative Learning in Human Agent Interaction -
Tomohiro Yamaguchi,Takuma Nishimura, Keiki Takadama
The International Conference on Humanized Systems 2012   OS02_1003    Aug 2012   [Refereed]
Awareness based filtering - Toward the Cooperative Learning in Human Agent Interaction -
Tomohiro Yamaguchi,Takuma Nishimura, Keiki Takadama
ICROS-SICE International Joint Conference (ICCAS-SICE 2009)   1164-1167   Aug 2009   [Refereed]
Multiple Timescales PIA for model based reinforcement learning
Yamaguchi, T., and Imatani, E.
Journal of Advanced Computational Intelligence and Intelligent Informatics   13(6) 658-666   2009   [Refereed]
How to recommend preferable solutions of a user in interactive reinforcement learning ?
Tomohiro Yamaguchi and Takuma Nishimura
SICE International Conference on Instrumentation, Control and Information Technology (SICE2008)   2050-2055   Aug 2008   [Refereed]
Multiple Timescales PIA for cooperative reinforcement learning based on MDP model
Tomohiro Yamaguchi and Eri Imatani
, SICE International Conference on Instrumentation, Control and Information Technology (SICE2007)   3C03-6   Sep 2007   [Refereed]

Misc

 
Mutnal Adaptation in Communication between a Human and a Life-like Agent by Sharing Context Dependent Facial Expressions
Proc. of 4th Asia-Pacitic Conference on Simulated Evolution And Learning (Seal2002)      2002
Acquiring emotion mappings through the interaction between a user and a life-like agent
Proc, of 9th Int. Conf. on Human-Computer Interaction(HCI2001)   1 993-997   2001
Mirror Agent : An Interface Agent that Mirrors and Supports User's Behaviors by Visualizing Gazing Lines
Proc. of 9th Int. Conf. on Human-Computer Interaction(HCI2001)Poster Session : Abridged Proceedings   394-398   2001
Interactive Self-Reflection based Reinforcement Learning for Multiagent Coordination
Proc. of 5rd Int. Symposium on Artificial Life and Robotics(AROB-2000)   2 442-445   2000
Interactive Self-Reflection based Multiagent Reinforcement Learning for Coordination
Proc. of The Third Asia-Pacific Conf. on Simulated Evolution And Learning(SEAL2000 in IECON-2000)   2885-2890   2000

Books etc

 
Advances in Reinforcement Learning
Yamaguchi, T., Nishimura, T. and Sato, K. (Part:Joint Work, How to recommend preferable solutions of a user in interactive reinforcement learning?)
InTech Open Access Publisher   Jan 2011   
PRICAI2002: Trends in Artificial Intelligence, LNAI 2417
Taro Konda, Shinjiro Tensyo, Tomohiro Yamaguchi (Part:Joint Work, Phased Method for Average Reward Reinforcement Learning - Preliminary Results -)
Springer, pp.208-217   2002   
PRICAI2002: Trends in Artificial Intelligence, LNAI2417
Taro Konda, Tomohiro Yamaguchi (Part:Joint Work, LC-Learning, Phased Method for Average Reward Reinforcement Learning - Analysis of Optimal Criteria -)
Springer, pp.198-207   2002   
Intelligent Agents and Multi-Agent Systems, LNAI2413
Yamada, S., Yamaguchi, T., (Part:Joint Work, ., Mutual Learning of Mind Reading between a Human and a Life-like Agent)
Springer, pp.138-150   2002   

Works

 
Mirror Agent : An Interface Agent that Mirrors and Supports User's Behaviors by Visualizing Gazing Lines
1999 - 2004
Interactive Self-Reflection based Autonomous Learning Mechanism of an Agent
1999 - 2003
Mirror Agent : An Interface Agent that Mirrors and Supports User's Behaviors by Visualizing Gazing Lines
2001
RAE-PIA : An efficient reinforcement learning method for an optimal policy under a multi-reward's environment
2001
Reinforcement Learning for a large-scale MDP problem by a group of Isomorphic POMDP agents
2001

Research Grants & Projects

 
Study on Learning and Evolution in Artificial Life
Study on Learning and Problem Solving
Behavior Based Robot Learning