Multitask Reinforcement Learning on the Distribution of MDPs (in Japanese)
IEEJ Transactions on Electronics, Information and Systems, Vol.123-C No.5 p.1004-1011
May 2003 [pdf, 260K]
Javier R. Movellan, Fumihide Tanaka, Ian R. Fasel, Cynthia Taylor, Paul Ruvolo and Micah Eckhardt
The RUBI Project: A Progress Report
Proceedings of the 2007 ACM/IEEE Second International Conference on Human-Robot Interaction (HRI 2007), p.333-339
Arlington, U.S.A., March 2007 [pdf, 1.7M]
Fumihide Tanaka and Javier R. Movellan
A Way of Implementing an Internal Reward for Autonomous Robots
International Workshop on Synergistic Intelligence Dynamics at Humanoids 2006
Genova, Italy, December 2006 [pdf, 14.8K]
Fumihide Tanaka and Javier R. Movellan
Behavior Analysis of Children's Touch on a Small Humanoid Robot: Long-term Observation at a Daily Classroom over Three Months
Proceedings of the 15th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2006), p.753-756
Hatfield, United Kingdom, September 2006 [pdf, 254K]
Fumihide Tanaka and Javier R. Movellan
The RUBI Project: Designing Everyday Robots by Immersion
Fifth International Conference on Development and Learning (ICDL 2006)
Bloomington, U.S.A., June 2006
Fumihide Tanaka, Javier R. Movellan, Bret Fortenberry and Kazuki Aisaka
Daily HRI Evaluation at a Classroom Environment: Reports from Dance Interaction Experiments
Proceedings of the 1st Annual Conference on Human-Robot Interaction (HRI 2006), p.3-9
Salt Lake City, U.S.A., March 2006 [pdf, 884K]
Fumihide Tanaka, Bret Fortenberry, Kazuki Aisaka and Javier R. Movellan
Developing Dance Interaction between QRIO and Toddlers in a Classroom Environment: Plans for the First Steps
Proceedings of the 2005 IEEE International Workshop on Robot and Human Interactive Communication (RO-MAN 2005), p.223-228
Nashville, U.S.A., August 2005 [pdf, 744K]
(Best Paper Award)
Javier R. Movellan, Fumihide Tanaka, Bret Fortenberry and Kazuki Aisaka
The RUBI/QRIO Project: Origins, Principles, and First Steps
Proceedings of 2005 4th IEEE International Conference on Development and Learning (ICDL 2005), p.80-86
Osaka, Japan, July 2005 [pdf, 765K]
Fumihide Tanaka, Bret Fortenberry, Kazuki Aisaka and Javier R. Movellan
Plans for Developing Real-time Dance Interaction between QRIO and Toddlers in a Classroom Environment
Proceedings of 2005 4th IEEE International Conference on Development and Learning (ICDL 2005), p.142-147
Osaka, Japan, July 2005 [pdf, 477K]
Fumihide Tanaka and Hirotaka Suzuki
Dance Interaction with QRIO: A Case Study for Non-boring Interaction by Using an Entrainment Ensemble Model
Proceedings of the 2004 IEEE International Workshop on Robot and Human Interactive Communication (RO-MAN 2004), p.419-424
Kurashiki, Japan, September 2004 [pdf, 471K]
Fumihide Tanaka, Kuniaki Noda, Tsutomu Sawada and Masahiro Fujita
Associated Emotion and its Expression in an Entertainment Robot QRIO
Proceedings of the 3rd International Conference on Entertainment Computing (ICEC 2004), p.499-504
Lecture Notes in Computer Science 3166, Springer 2004
Eindhoven, The Netherlands, September 2004 [pdf, 914K] Copyright: Springer-Verlag
Fumihide Tanaka and Masayuki Yamamura
Multitask Reinforcement Learning with Value Statistics
Proceedings of the 2003 SICE Symposium on Systems and Information (SSI 2003)
Sendai, Japan, November 2003 [pdf, 169K]
(Systems & Information Young Author's Award)
Fumihide Tanaka and Masayuki Yamamura
Exploiting Value Statistics for Similar Continuing Tasks
Proceedings of the 2003 IEEE International Workshop on Robot and Human Interactive Communication (RO-MAN 2003), p.271-276
Millbrae, U.S.A., October 2003 [pdf, 309K]
Fumihide Tanaka and Masayuki Yamamura
Multitask Reinforcement Learning on the Distribution of MDPs
Proceedings of the 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA 2003), p.1108-1113
Kobe, Japan, July 2003 [pdf, 341K]
Fumihide Tanaka and Masayuki Yamamura
Multitask Reinforcement Learning on the Distribution of MDPs (in Japanese)
IEEJ Transactions on Electronics, Information and Systems, Vol.123-C No.5 p.1004-1011
May 2003 [pdf, 260K]
Fumihide Tanaka
Adaptive Agent Technologies for Future House Architecture (in Japanese)
Architectural Institute of Japan, a Research Paper Competition, May 2002 [pdf, 125K]
(A Prize Essay Paper)
Fumihide Tanaka
Skill Knowledge Assimilation by Reinforcement Learning Agent
6th SIGART/AAAI Doctoral Consortium in IJCAI-2001
Seattle, U.S.A., August 2001
Fumihide Tanaka and Masayuki Yamamura
Reinforcement Learning Agent that is Capable of 2-dimensional Multitask Learning (in Japanese)
Proceedings of the 15th Annual Conference of Japanese Society for Artificial Intelligence (JSAI 2001)
Matsue, Japan, May 2001 [pdf, 67K]
(Best Paper Award)
Fumihide Tanaka and Masayuki Yamamura
An Approach to Lifelong Reinforcement Learning through Multiple Environments
Proceedings of the 6th European Workshop on Learning Robots (EWLR-6), p.93-99
Brighton, U.K., August 1997 [pdf, 171K]