| Nonparametric return distribution approximation for reinforcement learning T Morimura, M Sugiyama, H Kashima, H Hachiya, T Tanaka Proceedings of the 27th International Conference on Machine Learning (ICML …, 2010 | 270 | 2010 |
| Parametric return density estimation for reinforcement learning T Morimura, M Sugiyama, H Kashima, H Hachiya, T Tanaka arXiv preprint arXiv:1203.3497, 2012 | 132 | 2012 |
| Map matching with hidden Markov model on sampled road network R Raymond, T Morimura, T Osogami, N Hirosue Proceedings of the 21st international conference on pattern recognition …, 2012 | 79 | 2012 |
| これからの強化学習 牧野， 澁谷， 長史， 白川， 浅田 (No Title), 2016 | 44 | 2016 |
| Ibm mega traffic simulator T Osogami, T Imamichi, H Mizuta, T Morimura, R Raymond, T Suzumura, ... IBM Res., Tokyo, Japan, IBM Res. Rep. RT0896, 2012 | 43 | 2012 |
| Utilizing the natural gradient in temporal difference reinforcement learning with eligibility traces T Morimura, E Uchibe, K Doya International Symposium on Information Geometry and Its Applications, 256-263, 2005 | 40 | 2005 |
| City-wide traffic flow estimation from a limited number of low-quality cameras T Idé, T Katsuki, T Morimura, R Morris IEEE Transactions on Intelligent Transportation Systems 18 (4), 950-959, 2016 | 38 | 2016 |
| Solving inverse problem of Markov chain with partial observations T Morimura, T Osogami, T Idé Advances in neural information processing systems 26, 2013 | 38 | 2013 |
| Derivatives of logarithmic stationary distributions for policy gradient reinforcement learning T Morimura, E Uchibe, J Yoshimoto, J Peters, K Doya Neural computation 22 (2), 342-376, 2010 | 28 | 2010 |
| Updating policy parameters under Markov decision process system environment T Morimura, T Osogami, T Shirai US Patent 8,818,925, 2014 | 20 | 2014 |
| A generalized natural actor-critic algorithm T Morimura, E Uchibe, J Yoshimoto, K Doya Advances in neural information processing systems 22, 2009 | 20 | 2009 |
| Assistance generation T Katsuki, T Morimura US Patent 10,878,337, 2020 | 18 | 2020 |
| A new natural policy gradient by stationary distribution metric T Morimura, E Uchibe, J Yoshimoto, K Doya Machine Learning and Knowledge Discovery in Databases: European Conference …, 2008 | 16 | 2008 |
| 強化学習 森村哲郎 講談社, 2019 | 15 | 2019 |
| Cooperative neural network reinforcement learning S Dasgupta, T Morimura, T Osogami US Patent App. 15/647,543, 2019 | 14 | 2019 |
| Statistical origin-destination generation with multiple sources T Morimura, S Kato Proceedings of the 21st International Conference on Pattern Recognition …, 2012 | 14 | 2012 |
| A consistent method for graph based anomaly localization S Hara, T Morimura, T Takahashi, H Yanagisawa, T Suzuki Artificial intelligence and statistics, 333-341, 2015 | 13 | 2015 |
| Determining optimal action in consideration of risk T Morimura, T Osogami US Patent 8,639,556, 2014 | 12 | 2014 |
| Adaptive step-size policy gradients with average reward metric T Matsubara, T Morimura, J Morimoto Proceedings of 2nd Asian Conference on Machine Learning, 285-298, 2010 | 12 | 2010 |
| Identification of antibiotic clarithromycin binding peptide displayed by T7 phage particles T Morimura, N Noda, Y Kato, T Watanabe, T Saitoh, T Yamazaki, ... The Journal of Antibiotics 59 (10), 625-632, 2006 | 12 | 2006 |
Takayuki OsogamiIBM確認したメール アドレス: jp.ibm.com
