Tetsuro Morimura

Journals

• Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Jan Peters, and Kenji Doya: Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning, Neural Computation, Vol. 22, No. 2, pp. 342-376, 2010.
• Tetsuro Morimura, Eiji Uchibe, and Kenji Doya: Natural actor-critic with baseline adjustment for variance reduction, Artificial Life and Robotics, Vol. 13, No. 1, pp. 275-279, 2008.
• Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, Jan Peters, and Kenji Doya: A new natural gradient of average reward for policy search, The IEICE Transactions on Information and Systems (Japanese Edition), Vol. J91-D, No.6, pp.1515-1527, 2008.
• Tetsuro Morimura, Mio Hashiba, Hiroshi Kameda, Mihoko Takami, Hirokazu Takahama, Masahiko Ohshige, and Fumio Sugawara: Identification of Macrolide Antibiotic-binding Human_p8 Protein, The Journal of Antibiotics, Vol. 61, pp. 291-296, 2008.
• Tetsuro Morimura, Naoko Noda, Yasutaro Kato, Tetsuaki Watanabe, Takeki Saitoh,Takayuki Yamazaki, Keiichi Takada, Satoko Aoki, Keisuke Ohta, Masahiko Ohshige, Kengo Sakaguchi, and Fumio Sugawara: Identification of Antibiotic Clarithromycin Binding Peptide Displayed by T7 Phage Particles, The Journal of Antibiotics, Vol. 59, pp. 625-632, 2006.

Major Conferences

• Tetsuro Morimura, Masashi Sugiyama, Hisashi Kashima, Hirotaka Hachiya, and Toshiyuki Tanaka: Nonparametric Return Distribution Approximation for Reinforcement Learning, In Proc. 27th International Conference on Machine Learning (ICML2010), to appear.
• Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, and Kenji Doya: A Generalized Natural Actor-Critic Algorithm, In Proc. 23st Annual Conference on Neural Information Processing Systems (NIPS2009), pp. 1312-1320, 2010.
• Masashi Sugiyama, Hirotaka Hachiya, Hisashi Kashima, and Tetsuro Morimura: Least Absolute Policy Iteration for Robust Value Function Approximation, In Proc. 2009 IEEE International Conference on Robotics and Automation (ICRA2009), pp. 2904-2909, 2009.
• Tetsuro Morimura, Eiji Uchibe, Junichiro Yoshimoto, and Kenji Doya: A new natural policy gradient by stationary distribution metric, Machine Learning and Knowledge Discovery in Databases, Vol. 5212, pp. 82-97, 2008. (presented at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2008.)

• Tetsuro Morimura, Eiji Uchibe, and Kenji Doya: Utilizing Natural Gradient in Temporal Difference Reinforcement Learning with Eligibility Traces, In Proc. 2nd International Symposium on Information Geometry and its Applications (IGAIA 2005), pp. 256-263, 2005.

Invited Talks

• Tetsuro Morimura: Risk-sensitive and robust reinforcement learning with estimating return distribution,, Global COE, Knowledge Grid Computing Core Seminar, Kyoto university, Japan, Jun. 12, 2009.

Education

• Mar. 2003: Bachelor of Science from Applied Biological Science, Faculty of Science and Technology, Tokyo University of Science, Chiba, Japan.
• Mar. 2005: Master of Engineering from Department of Bioinformatics and Genomics, Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan.
• Mar. 2008: Doctor of Engineering from Department of Bioinformatics and Genomics, Graduate School of Information Science, Nara Institute of Science and Technology, Nara, Japan.

Employment

• Aug. 2004 – Mar. 2008: Research Assistant, Neural Computation Unit, Okinawa Institute of Science and Technology, Okinawa, Japan.
• Since Apr. 2008: Researcher, IBM Research - Tokyo, IBM Japan, Ltd., Kanagawa, Japan.