論文

• Yamada, M., Suzuki, T., Kanamori, T., Hachiya, H., Sugiyama, M.. Relatiive density-ratio estimationfor robust distribution comparision, Neural Computation, vol. 25, no. 5, pp. 1324-1370, 2013.
• Ning XIE, Hachiya, H., Sugiyama, M.. Artist agent:A reinforcemnet learning approach to automatic stroke generation in oriental ink painting, IEICE Transzctions on Information and Systems, vol. E96-D, no. 5, pp. 1134-1144, 2013.
• Zhao, T., Hachiya, H., Tangkaratt, V., Morimoto, J., & Sugiyama, M.. Efficient sample reuse inpolicy gradients with parameter-based exploration, Neural Computation, vol. 25, no. 6, pp. 1512-1547, 2013.
• Jitkrittum, W., Hachiya, H., & Sugiyama, M.. Feature selection via 11-penalized squared-loss mutual information, IEICE Transactions on Information and Systems, vol. E96-D, no. 7, pp. 1513-1524, 2013.
• H Nam, Hachiya, H., & Sugiyama, M.. Computationally efficient multi-label classification by least-squares probabilistic classifiers, IEICE Transactions on Information and Systems, vol. E96-D, no. 8, pp. 1871-1974, 2013.
• Sugiyama, M., Gang, N., Yamada, M., Kimura, M., & Hachiya, H.. Information-maximization clustering based on squared-loss mutual information, Neural Computation, 2013.
• Zhao, T., Hachiya, H., Niu, G., Sugiyama, M.. Analysis and improvement of policy gradient estimation, Neural Networks, vol. 26, pp. 118-129, 2012.
• Simm, J., Sugiyama, M., Hachiya, H.. Multi-task approach to reinforcement learning for factored-state Markov decision problems, IEICE, IEICE Transactions on Information and Systems, vol. E95-D, no. 10, pp. 2426-2437, 2012.
• Hachiya, H., Sugiyama, M., Ueda, N.. Importance-weighted least-squares probabilistic classifier for covariate shift adapptation with application to human activity recognition, Neurocomputing, vol. 80, pp. 93-101, 2012.
• Hachiya, H., Peters, J., Sugiyama, M.. Reward weighted regression with sample reuse for direct policy search in reinforcement learnig, Neural Computation, vol. 23, no. 11, pp. 2798-2832, 2011.
• Sugiyama, M., Takeuchi, I., Kanamori, T., Suzuki, T., Hachiya, H., Okanohara, D.. Least-squares conditional density estimation., IEICE Transactions on Infromation and Systems,, IEICE, Vol. E93-D, no. 3, pp. 583-594, 2010.
• Sugiyama, M., Hachiya, H., Kashima, H., Morimura, T.. Least absolute policy iteration---A robust approach to value function approximation., IEICE, IEICE Transactions on Information and Systems., Vol. E93-D, no. 9, pp. xxx-xxx, 2010.
• Akiyama, T., Hachiya, H., Sugiyama, M.. Efficient exploration through active learning for value function approximation in reinforcement learning., NeuralNetworks, Vol. 23, no. 5, pp. 639-648, 2010.
• Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.. Adaptive importance sampling for value function approximation in off-policy reinforcement learning., Neural Networks, vol. 22, no. 10, pp. 1399-1410, 2009.
• Masashi Sugiyama, Hirotaka Hachiya, Christopher Towell, Sethu Vijayakumar. Geodesic Gaussian kernels for value function approximation, Autonomous Robots, Vol. 25, No. 3, pp. 287-304, 2008.

著書

• Hachiya, H., Morimura, T., Sugiyama, M.. Statistical Reinforcement Learning: Modern Machine Learning Approaches, Chapman & Hall/CRC Press, 2015.
• 八谷大岳, 杉山将. 強くなるロボティック・ゲームプレイヤーの作り方～実戦で学ぶ強化学習, 毎日コミュニケーションズ、東京、2008, page 219, Aug. 2008.
• Hachiya, H., Sugiyama, M. Training Robotic Game Players by Reinforcement Learning, Training Robotic Game Players by Reinforcement Learning, Mainichi Communications, 2008.

国際会議発表 (査読有り)

• Gang Niu, B Dai, Hirotaka Hachiya, Masashi Sugiyama, Wittawat Jitkrittum. Squared-loss mutual information regularization, ICML2013,JMLR Workshop and Conference, In S.Dasgupta and D.McAllester(Eds.), pp. 10-18, 2013.
• Niu, G., Jitkrittum, W., Hachiya, H., Dai, B., Sugiyama, M.. Squared-loss mutual information regularization., IBISML2011, IEICE Technical Report, IBISML2011-108, pp. 147-153, Mar. 2012.
• Zhao, T., Hachiya, H., Sugiyama, M.. Importance-weighted policy gradients with parameter-based exploration., IBISML2011, IEICE Technical Report, IBISML2011-95, pp. 55-62, Mar. 2012.
• Jitkrittum, W., Hachiya, H., Sugiyama, M.. Feature selection via l1-penalized squared-loss mutual information., IBISML2011, IEICE Technical Report, IBISML2011-197, pp. 139-146, Mar. 2012.
• Sugiyama, M., Yamada, M., Kimura, M., Hachiya, H.. Information-maximization clustering: Analytic solution and model selection., IEICE Technical Report, IBISML2010-114, pp. 69-76, Feb. 2012.
• Hachiya, H., Sugiyama, M.. Feature selection for reinforcement learning: Evaluating implicit state-reward dependency via conditional mutual information., the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD2010),, In Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science, vol. 6321, pp. 474-489, Sept. 2010.
• Morimura, T., Sugiyama, M., Kashima, H., Hachiya, H., Tanaka, T.. Parametric return density estimation for reinforcement learning., the 26th Conference on Uncertainty in Artificial Intelligence (UAI2010), In Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence(UAI2010), July 2010.
• Morimura, T., Sugiyama, M., Kashima, H., Hachiya, H., Tanaka, T.. Nonparametric return distribution approximation for reinforcement learning., 27th International Conference on Machine Learning (ICML2010), Proceeding of 27th International Conference on Machine Learning(ICML2010), June 2010.
• Hachiya, H., Sugiyama, M.. New feature selection method for reinforcement learning: Conditional mutual information reveals implicit state-reward dependency., IBISML2010-21, IEICE Technical Report, IBISML2010-21, pp. 137-144, June 2010.
• Sugiyama, M., Takeuchi, I., Kanamori, T., Suzuki, T., Hachiya, H., Okanohara, D.. Conditional density estimation via least-squares density ratio estimation., Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS2010), In Proceedings of Thirteenth Conference on Artificial Intelligence and Statistics (AISTATS2010),, Vol. 9, pp. 781-788, May 2010.
• Simm, J., Sugiyama, M., Hirotaka Hachiya. Improving model-based reinforcement learning with multitask learning., IPSJSIGMathematicalModellingandProblemSolving,, IPSJSIGTechnicalReport,, Vol. 2009-MPS-76, no. 3, pp. 1-8, Dec. 2009.
• Sugiyama, M., Takeuchi, I., Suzuki, T., Kanamori, T., Hachiya, H., Okanohara, D.. Conditional density estimation based on density ratio estimation., IPSJSIGMathematicalModelling and ProblemSolving,, IPSJSIGTechnicalReport,, Vol. 2009-MPS-76, no. 4, Dec. 2009.
• Morimura, T., Sugiyama, M., Kashima, H., Hachiya, H., Tanaka, T.. Return distribution estimation for risk-sensitive reinforcement learning., 2009Workshop on Information-Based Induction Sciences(IBIS2009), Oct. 2009.
• Simm, J., Sugiyama, M., Hachiya, H.. Observational reinforcement learning., 2009Workshop on Information-Based Induction Sciences(IBIS2009), Proceedings of 2009 Workshop on Information-Based Induction Sciences (IBIS2009),, Oct. 2009.
• Sugiyama, M., Hachiya, H., Kashima, H., Morimura, T.. Least absolute policy iteration for robust value function approximation., 2009 IEEE International Conference on Robotics and Automation, Proceeding of IEEE International Conference on Robotics and Automation(ICRA2009), pp. 2904-2909, May 2009.
• Sugiyama. M., Hachiya, H., Akiyama, T.. Robot control by reinforcement learning: A machine-learning approach., the 9th Control Division Conference, In Proceedings of the Society of Instrument and Control Engineers, no. FC1-3, Mar. 2009.
• Akiyama, T., Hachiya, H., Sugiyama, M.. Active policy iteration: Efficient exploration through active learning for value function approximation in reinforcement learning., the Twenty-First International Joint Conference on Artificial Intelligence(IJCAI2009), In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI2009),, pp. 980-985, 2009.
• Hachiya, H., Peters, J., & Sugiyama, M.. Efficient sample reuse in EM-based policy search., the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases(ECML-PKDD2009), Machine Learning and Knowledge Discovery in Databases,, Berlin, Springer, vol. 5781, pp. 469-484, 2009.
• Akiyama, T., Hachiya, H., Sugiyama. M.. Statistical active learning for efficient value function approximation in reinforcement learning., Meeting of IEICE Neurocomputing (NC) Technical Group,, IEICE Technical Report, NC2008-147, pp. 261-266, 2009.
• Hachiya, H., Peters, J., Sugiyama. M.. Adaptive importance sampling with automatic model selection in reward weighted regression., Meeting of IEICE Neurocomputing(NC) Technical Group, IEICE Technical Report, NC2008-145,, pp. 249-254, 2009.
• Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.. Efficient data reuse in value function approximation., In Proceeding of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL2009), pp. 8-15, 2009.
• Akiyama, T., Hachiya, H., Sugiyama, M.. Efficient exploration through active learning for value function approximation in reinforcement learning., The Fourth International Workshop on Data-Mining and Statistical Science(DMSS2009), Proceeding of The Fourth International Workshop on Data-Mining and Statistical Science(DMSS2009), pp. 1-21, 2009.
• Akiyama, T., Hachiya, H., Sugiyama, M.. A new method of model selection for value function approximation in reinforcement learning., the Japanese Society for Artificial Intelligence, In Proceeding of the Japanese Society for Artificial Intelligence,, pp. 55-60, 2008.
• Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.. Adaptive importance sampling with automatic model selection in value function approximation, the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08), In Proceeding of the Twenty -Third AAAI Conference on Artificial Intelligence(AAAI2008), pp. 1351-1356, 2008.
• Masashi Sugiyama, Hirotaka Hachiya, Christopher Towell, Sethu Vijayakumar. Value function approximation on non-linear manifolds for robot motor control, 2007 IEEE International Conference on Robotics and Automation (ICRA 2007), Proc. 2007 IEEE International Conference on Robotics and Automation (ICRA 2007), pp. 1733-1740, Apr. 2007.
• Sugiyama, M., Hachiya, H., Towell, C., Vijayakumar, S.. Geodesic Gaussian kernels for value function approximation., 2006 Workshop on Information-Based Induction Science(IBIS2006), In Proceeding of 2006 Workshop on Information-Based Induction Science(IBIS2006), pp. 316-321, 2006.

国内会議発表 (査読有り)

• 高木 潤, 杉山 将, 木村 昭悟, 八谷 大岳, 大石 康智, 山田 誠.. 簡易半教師付確率的分類器を用いた自動メディアアノテーション, 画像の認識・理解シンポジウム2012 (MIRU2012), 画像の認識・理解シンポジウム2012 (MIRU2012)論文集, Aug. 2012.
• Morimura, T., Sugiyama, M., Kashima, H., Hachiya, H., Tanaka, T.. Return density estimation with dynamic programming., 2010 Workshop on Information-Based Induction Sciences (IBIS2010), IEICE Technical Report, IBISML2010-98, pp. 283-290, Nov. 2010.
• Morimura, T., Sugiyama, M., Kashima, H., Hachiya, H., Tanaka, T.. Convergence analysis of dynamic programming for distributional Bellman equation, Electronics, Information and Systems Conference, Electronics, Information and Systems Society, pp. 178-183, Sept. 2010.
• Hirotaka Hachiya, Takayuki Akiyama, Masashi Sugiyama. Efficient sample reuse by covariate shift adaptation in value function approximation, NIPS2007 Workshop on Robotics Challenges for Machine Learning, NIPS2007 Workshop on Robotics Challenges for Machine Learning, Dec. 2007.
• Hirotaka Hachiya, Masashi Sugiyama. Robot control by least-squares policy iteration with geodesic Gaussian kernels, the 21st Annual Conference of The Japanese Society for Artificial Intelligence (JSAI2007), no. 3D9-2, June 2007.

国際会議発表 (査読なし・不明)

• Sugiyama, M., Yamada, M., Kimura, M., Hachiya, H.. On information-maximization clustering: tuning parameter selection and analytic solution., 28th International Conference on Machine Learning (ICML2011), 28th International Conference on Machine Learning (ICML2011), Feb. 2012.
• Yamada, M., Suzuki, T., Kanamori, T., Hachiya, H., Sugiyama, M.. Relative density-ratio estimation for robust distribution comparison., Neural Information Processing Systems (NIPS2011),, Advances in Neural Information Processing Systems 24, pp. 594-602, Dec. 2011.
• Zhao, T., Hachiya, H., Niu, G., Sugiyama, M. Analysis and improvement of policy gradient estimation., Neural Information Processing Systems (NIPS2011),, Advances in Neural Information Processing Systems 24, J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, and K. Q. Weinberger, pp. 262-270, Dec. 2011.
• Hachiya, H., Akiyama, T., Sugiyama, M.. Adaptive importance sampling with automatic model selection in value function approximation, IEICE Neurocomputing (NC) Technical Group, IEICE Technical Report,NC2007-84,, pp. 75-80, 2007.

国内会議発表 (査読なし・不明)

• Takagi, J., Sugiyama, M., Kimura, A., Hachiya, H., Ohishi, Y., & Yamada, M.. Automatic media annotation with simple semi-supervised probabilitic classifiers, Meeting on Image Recognition and Understanding 2012, Aug. 2012.
• Zhao, T., Hachiya, H., Niu, G., Sugiyama, M.. Analysis and improvement of policy gradient estimation., IBISML2011, IEICE Technical Report, IBISML2011-12, pp. .83-89,, Feb. 2012.
• Nam, H., Hachiya, H., Sugiyama, M.. Computationally efficient multi-label classification by least-squares probabilistic classifier., IBISML2011, IEICE Technical Report, IBISML2011-73, pp. 213-216, Feb. 2012.
• Hachiya, H., Morimura, T., Makino, T., Sugiyama, M.. Modified Newton approach to policy search., IBISML2011, IEICE Technical Report, IBISML2011-54, pp. 79-85, Feb. 2012.
• 森村 哲郎, 杉山 将, 鹿島 久嗣, 八谷 大岳, 田中 利幸.. 動的計画法によるリターン分布推定., IBISML2010, 電子情報通信学会技術研究報告, IBISML2010-98,, pp. 283-290, Feb. 2012.
• Zhao, T., Hachiya, H., & Sugiyama, M.. Efficient data reuse in robot control learning via importnace sampling, 2nd Institute of Mathematical Statistics Asia Pacific Rim Meeting, 2012.
• Xie, N., Hachiya, H., Sugiyama, M.. Artist agent (A^2): Stroke painterly rendering based on reinforcement learning., IBISML2011, IEICE Technical Report, IBISML2011-30, pp. 119-126, Sept. 2011.
• Hachiya, H., Sugiyama, M., Ueda, N.. Importance-weighted least-squares probabilistic classifier for covariate shift adaptation with application to human activity recognition., The 5th International Workshop on Data-Mining and Statistical Science (DMSS2011),, Mar. 2011.
• 森村 哲郎, 杉山 将, 鹿島 久嗣, 八谷 大岳, 田中 利幸.. 分布Bellman方程式における動的計画法の収束性解析, 電気学会 電子・情報・システム部門大会, 電気学会 電子・情報・システム部門大会, pp. 178-183, Sept. 2010.
• Takayuki Akiyama, Hirotaka Hachiya, Masashi Sugiyama. A new method of model selection for value function approximation in reinforcement learning, Japanese Society for Artificial Intelligence, 6th Meeting of Special Interest Group on Data Mining and Statistical Mathematics, Feb. 2008.
• 八谷 大岳. 状態行動価値関数近似における自動モデル選択による適応的重要度サンプリング, 東京工業大学グローバル COE 「計算世界観の深化と展開」発足シンポジウム, Dec. 2007.

[ BibTeX 形式で保存 ]    [ 論文・著書をCSV形式で保存 ]    [ 特許をCSV形式で保存 ]