@book{CTT100619593,
  author = {Hachiya, H. and Morimura, T. and Sugiyama, M.},
  title = {Statistical Reinforcement Learning: Modern Machine Learning Approaches},
  publisher = {},
  year = 2015,
}

@book{CTT100660192,
  author = {八谷大岳 and 杉山将},
  title = {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},
  publisher = {毎日コミュニケーションズ、東京、2008},
  year = 2008,
}

@book{CTT100572501,
  author = {Hachiya, H. and Sugiyama, M},
  title = {Training Robotic Game Players by Reinforcement Learning},
  publisher = {Mainichi Communications},
  year = 2008,
}

@article{CTT100660176,
  author = {Yamada, M. and Suzuki, T. and Kanamori, T. and Hachiya, H. and Sugiyama, M.},
  title = {Relatiive density-ratio estimationfor robust distribution comparision},
  journal = {Neural Computation},
  year = 2013,
}

@article{CTT100660174,
  author = {Ning XIE and Hachiya, H. and Sugiyama, M.},
  title = {Artist  agent:A reinforcemnet learning approach to automatic stroke generation in oriental ink painting},
  journal = {IEICE Transzctions on Information and Systems},
  year = 2013,
}

@article{CTT100660173,
  author = {Zhao, T. and Hachiya, H. and Tangkaratt, V. and Morimoto, J. and & Sugiyama, M.},
  title = {Efficient sample reuse inpolicy gradients with parameter-based exploration},
  journal = {Neural Computation},
  year = 2013,
}

@article{CTT100660169,
  author = {Jitkrittum, W. and Hachiya, H. and & Sugiyama, M.},
  title = {Feature selection via 11-penalized squared-loss mutual information},
  journal = {IEICE Transactions on Information and Systems},
  year = 2013,
}

@article{CTT100660153,
  author = {H Nam and Hachiya, H. and & Sugiyama, M.},
  title = {Computationally efficient multi-label classification by least-squares probabilistic classifiers},
  journal = {IEICE Transactions on Information and Systems},
  year = 2013,
}

@article{CTT100660142,
  author = {Sugiyama, M. and Gang, N. and Yamada, M. and Kimura, M. and & Hachiya, H.},
  title = {Information-maximization clustering based on squared-loss mutual information},
  journal = {Neural Computation},
  year = 2013,
}

@article{CTT100660280,
  author = {Zhao, T. and Hachiya, H. and Niu, G. and Sugiyama, M.},
  title = {Analysis and improvement of policy gradient estimation},
  journal = {Neural Networks},
  year = 2012,
}

@article{CTT100660269,
  author = {Simm, J. and Sugiyama, M. and Hachiya, H.},
  title = {Multi-task approach to reinforcement learning for factored-state Markov decision problems},
  journal = {},
  year = 2012,
}

@article{CTT100660281,
  author = {Hachiya, H. and Sugiyama, M. and Ueda, N.},
  title = {Importance-weighted least-squares probabilistic classifier for covariate shift adapptation with application to human activity recognition},
  journal = {Neurocomputing},
  year = 2012,
}

@article{CTT100660282,
  author = {Hachiya, H. and Peters, J. and Sugiyama, M.},
  title = {Reward weighted regression with sample reuse for direct policy search in reinforcement learnig},
  journal = {Neural Computation},
  year = 2011,
}

@article{CTT100604103,
  author = {Sugiyama, M. and Takeuchi, I. and Kanamori, T. and Suzuki, T. and Hachiya, H. and Okanohara, D.},
  title = {Least-squares conditional density estimation.},
  journal = {IEICE Transactions on Infromation and Systems,},
  year = 2010,
}

@article{CTT100607876,
  author = {Sugiyama, M. and Hachiya, H. and Kashima, H. and Morimura, T.},
  title = {Least absolute policy iteration---A robust approach to value function approximation.},
  journal = {IEICE Transactions on Information and Systems.},
  year = 2010,
}

@article{CTT100599751,
  author = {Akiyama, T. and Hachiya, H. and Sugiyama, M.},
  title = {Efficient exploration through active learning for value function approximation in reinforcement learning.},
  journal = {NeuralNetworks},
  year = 2010,
}

@article{CTT100572427,
  author = {Hachiya, H. and Akiyama, T. and Sugiyama, M. and Peters, J.},
  title = {Adaptive importance sampling for value function approximation in off-policy reinforcement learning.},
  journal = {Neural Networks},
  year = 2009,
}

@article{CTT100575765,
  author = {Masashi Sugiyama and Hirotaka Hachiya and Christopher Towell and Sethu Vijayakumar},
  title = {Geodesic Gaussian kernels for value function approximation},
  journal = {Autonomous Robots},
  year = 2008,
}

@inproceedings{CTT100660077,
  author = {Gang Niu and B Dai and Hirotaka Hachiya and Masashi Sugiyama and Wittawat Jitkrittum},
  title = {Squared-loss mutual information regularization},
  booktitle = {},
  year = 2013,
}

@inproceedings{CTT100641861,
  author = {高木 潤 and 杉山 将 and 木村 昭悟 and 八谷 大岳 and 大石 康智 and 山田 誠.},
  title = {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},
  booktitle = {画像の認識・理解シンポジウム2012 (MIRU2012)論文集},
  year = 2012,
}

@inproceedings{CTT100660126,
  author = {Takagi, J. and Sugiyama, M. and Kimura, A. and Hachiya, H. and Ohishi, Y. and & Yamada, M.},
  title = {Automatic media annotation with simple semi-supervised probabilitic classifiers},
  booktitle = {},
  year = 2012,
}

@inproceedings{CTT100634714,
  author = {Niu, G. and Jitkrittum, W. and Hachiya, H. and Dai, B. and Sugiyama, M.},
  title = {Squared-loss mutual information regularization.},
  booktitle = {IEICE Technical Report, IBISML2011-108},
  year = 2012,
}

@inproceedings{CTT100634727,
  author = {Zhao, T. and Hachiya, H. and Sugiyama, M.},
  title = {Importance-weighted policy gradients with parameter-based exploration.},
  booktitle = {IEICE Technical Report, IBISML2011-95},
  year = 2012,
}

@inproceedings{CTT100634717,
  author = {Jitkrittum, W. and Hachiya, H. and Sugiyama, M.},
  title = {Feature selection via l1-penalized squared-loss mutual information.},
  booktitle = {IEICE Technical Report, IBISML2011-197},
  year = 2012,
}

@inproceedings{CTT100633501,
  author = {Zhao, T. and Hachiya, H. and Niu, G. and Sugiyama, M.},
  title = {Analysis and improvement of policy gradient estimation.},
  booktitle = {IEICE Technical Report, IBISML2011-12},
  year = 2012,
}

@inproceedings{CTT100633475,
  author = {Sugiyama, M. and Yamada, M. and Kimura, M. and Hachiya, H.},
  title = {On information-maximization clustering: tuning parameter selection and analytic solution.},
  booktitle = {28th International Conference on Machine Learning (ICML2011)},
  year = 2012,
}

@inproceedings{CTT100633490,
  author = {Sugiyama, M. and Yamada, M. and Kimura, M. and Hachiya, H.},
  title = {Information-maximization clustering: Analytic solution and model selection.},
  booktitle = {IEICE Technical Report, IBISML2010-114},
  year = 2012,
}

@inproceedings{CTT100633507,
  author = {Nam, H. and Hachiya, H. and Sugiyama, M.},
  title = {Computationally efficient multi-label classification by least-squares probabilistic classifier.},
  booktitle = {IEICE Technical Report, IBISML2011-73},
  year = 2012,
}

@inproceedings{CTT100633510,
  author = {Hachiya, H. and Morimura, T. and Makino, T. and Sugiyama, M.},
  title = {Modified Newton approach to policy search.},
  booktitle = {IEICE Technical Report, IBISML2011-54},
  year = 2012,
}

@inproceedings{CTT100633555,
  author = {森村 哲郎 and 杉山 将 and 鹿島 久嗣 and 八谷 大岳 and 田中 利幸.},
  title = {動的計画法によるリターン分布推定.},
  booktitle = {電子情報通信学会技術研究報告, IBISML2010-98,},
  year = 2012,
}

@inproceedings{CTT100660130,
  author = {Zhao, T. and Hachiya, H. and & Sugiyama, M.},
  title = {Efficient data reuse in robot control learning via importnace sampling},
  booktitle = {},
  year = 2012,
}

@inproceedings{CTT100633485,
  author = {Yamada, M. and Suzuki, T. and Kanamori, T. and Hachiya, H. and Sugiyama, M.},
  title = {Relative density-ratio estimation for robust distribution comparison.},
  booktitle = {Advances in Neural Information Processing Systems 24},
  year = 2011,
}

@inproceedings{CTT100633484,
  author = {Zhao, T. and Hachiya, H. and Niu, G. and Sugiyama, M},
  title = {Analysis and improvement of policy gradient estimation.},
  booktitle = {Advances in Neural Information Processing Systems 24},
  year = 2011,
}

@inproceedings{CTT100633503,
  author = {Xie, N. and Hachiya, H. and Sugiyama, M.},
  title = {Artist agent (A^2): Stroke painterly rendering based on reinforcement learning.},
  booktitle = {IEICE Technical Report, IBISML2011-30},
  year = 2011,
}

@inproceedings{CTT100633493,
  author = {Hachiya, H. and Sugiyama, M. and Ueda, N.},
  title = {Importance-weighted least-squares probabilistic classifier for covariate shift adaptation with application to human activity recognition.},
  booktitle = {},
  year = 2011,
}

@inproceedings{CTT100619619,
  author = {Morimura, T. and Sugiyama, M. and Kashima, H. and Hachiya, H. and Tanaka, T.},
  title = {Return density estimation with dynamic programming.},
  booktitle = {IEICE Technical Report, IBISML2010-98},
  year = 2010,
}

@inproceedings{CTT100619611,
  author = {Morimura, T. and Sugiyama, M. and Kashima, H. and Hachiya, H. and Tanaka, T.},
  title = {Convergence analysis of dynamic programming for distributional Bellman equation},
  booktitle = {Electronics, Information and Systems Society},
  year = 2010,
}

@inproceedings{CTT100611622,
  author = {Hachiya, H. and Sugiyama, M.},
  title = {Feature selection for reinforcement learning: Evaluating implicit state-reward dependency via conditional mutual information.},
  booktitle = {In Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science},
  year = 2010,
}

@inproceedings{CTT100633549,
  author = {森村 哲郎 and 杉山 将 and 鹿島 久嗣 and 八谷 大岳 and 田中 利幸.},
  title = {分布Bellman方程式における動的計画法の収束性解析},
  booktitle = {電気学会 電子・情報・システム部門大会},
  year = 2010,
}

@inproceedings{CTT100608869,
  author = {Morimura, T. and Sugiyama, M. and Kashima, H. and Hachiya, H. and Tanaka, T.},
  title = {Parametric return density estimation for reinforcement learning.},
  booktitle = {In Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence(UAI2010)},
  year = 2010,
}

@inproceedings{CTT100608861,
  author = {Morimura, T. and Sugiyama, M. and Kashima, H. and Hachiya, H. and Tanaka, T.},
  title = {Nonparametric return distribution approximation for reinforcement learning.},
  booktitle = {Proceeding of 27th International Conference on Machine Learning(ICML2010)},
  year = 2010,
}

@inproceedings{CTT100611624,
  author = {Hachiya, H. and Sugiyama, M.},
  title = {New feature selection method for reinforcement learning: Conditional mutual information reveals implicit state-reward dependency.},
  booktitle = {IEICE Technical Report, IBISML2010-21},
  year = 2010,
}

@inproceedings{CTT100605114,
  author = {Sugiyama, M. and Takeuchi, I. and Kanamori, T. and Suzuki, T. and Hachiya, H. and Okanohara, D.},
  title = {Conditional density estimation via least-squares density ratio estimation.},
  booktitle = {In Proceedings of Thirteenth Conference on Artificial Intelligence and Statistics (AISTATS2010),},
  year = 2010,
}

@inproceedings{CTT100599773,
  author = {Simm, J. and Sugiyama, M. and Hirotaka Hachiya},
  title = {Improving model-based reinforcement learning with multitask learning.},
  booktitle = {IPSJSIGTechnicalReport,},
  year = 2009,
}

@inproceedings{CTT100599769,
  author = {Sugiyama, M. and Takeuchi, I. and Suzuki, T. and Kanamori, T. and Hachiya, H. and Okanohara, D.},
  title = {Conditional density estimation based on density ratio estimation.},
  booktitle = {IPSJSIGTechnicalReport,},
  year = 2009,
}

@inproceedings{CTT100591983,
  author = {Morimura, T. and Sugiyama, M. and Kashima, H. and Hachiya, H. and Tanaka, T.},
  title = {Return distribution estimation for risk-sensitive reinforcement learning.},
  booktitle = {},
  year = 2009,
}

@inproceedings{CTT100591982,
  author = {Simm, J. and Sugiyama, M. and Hachiya, H.},
  title = {Observational reinforcement learning.},
  booktitle = {Proceedings of 2009 Workshop on Information-Based Induction Sciences (IBIS2009),},
  year = 2009,
}

@inproceedings{CTT100576712,
  author = {Sugiyama, M. and Hachiya, H. and Kashima, H. and Morimura, T.},
  title = {Least absolute policy iteration for robust value function approximation.},
  booktitle = {Proceeding of IEEE International Conference on Robotics and Automation(ICRA2009)},
  year = 2009,
}

@inproceedings{CTT100573630,
  author = {Sugiyama. M. and Hachiya, H. and Akiyama, T.},
  title = {Robot control by reinforcement learning: A machine-learning approach.},
  booktitle = {In Proceedings of the Society of Instrument and Control Engineers},
  year = 2009,
}

@inproceedings{CTT100588656,
  author = {Akiyama, T. and Hachiya, H. and Sugiyama, M.},
  title = {Active policy iteration: Efficient exploration through active learning for value function approximation in reinforcement learning.},
  booktitle = {In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI2009),},
  year = 2009,
}

@inproceedings{CTT100589536,
  author = {Hachiya, H. and Peters, J. and & Sugiyama, M.},
  title = {Efficient sample reuse in EM-based policy search.},
  booktitle = {Machine Learning and Knowledge Discovery in Databases,},
  year = 2009,
}

@inproceedings{CTT100573625,
  author = {Akiyama, T. and Hachiya, H. and Sugiyama. M.},
  title = {Statistical active learning for efficient value function approximation in reinforcement learning.},
  booktitle = {IEICE Technical Report, NC2008-147},
  year = 2009,
}

@inproceedings{CTT100573624,
  author = {Hachiya, H. and Peters, J. and Sugiyama. M.},
  title = {Adaptive importance sampling with automatic model selection in reward weighted regression.},
  booktitle = {IEICE Technical Report, NC2008-145,},
  year = 2009,
}

@inproceedings{CTT100573617,
  author = {Hachiya, H. and Akiyama, T. and Sugiyama, M. and Peters, J.},
  title = {Efficient data reuse in value function approximation.},
  booktitle = {In Proceeding of the 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL2009)},
  year = 2009,
}

@inproceedings{CTT100585257,
  author = {Akiyama, T. and Hachiya, H. and Sugiyama, M.},
  title = {Efficient exploration through active learning for value function approximation in reinforcement learning.},
  booktitle = {Proceeding of The Fourth International Workshop on Data-Mining and Statistical Science(DMSS2009)},
  year = 2009,
}

@inproceedings{CTT100575836,
  author = {Takayuki Akiyama and Hirotaka Hachiya and Masashi Sugiyama},
  title = {A new method of model selection for value function approximation in reinforcement learning},
  booktitle = {},
  year = 2008,
}

@inproceedings{CTT100576903,
  author = {Akiyama, T. and Hachiya, H. and Sugiyama, M.},
  title = {A new method of model selection for value function approximation in reinforcement learning.},
  booktitle = {},
  year = 2008,
}

@inproceedings{CTT100574090,
  author = {Hachiya, H. and Akiyama, T. and Sugiyama, M. and Peters, J.},
  title = {Adaptive importance sampling with automatic model selection in value function approximation},
  booktitle = {In Proceeding of the Twenty -Third AAAI Conference on Artificial Intelligence(AAAI2008)},
  year = 2008,
}

@inproceedings{CTT100575763,
  author = {八谷 大岳},
  title = {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},
  booktitle = {},
  year = 2007,
}

@inproceedings{CTT100575764,
  author = {Hirotaka Hachiya and Takayuki Akiyama and Masashi Sugiyama},
  title = {Efficient sample reuse by covariate shift adaptation in value function approximation},
  booktitle = {NIPS2007 Workshop on Robotics Challenges for Machine Learning},
  year = 2007,
}

@inproceedings{CTT100575843,
  author = {Hirotaka Hachiya and Masashi Sugiyama},
  title = {Robot control by least-squares policy iteration with geodesic Gaussian kernels},
  booktitle = {},
  year = 2007,
}

@inproceedings{CTT100574191,
  author = {Masashi Sugiyama and Hirotaka Hachiya and Christopher Towell and Sethu Vijayakumar},
  title = {Value function approximation on non-linear manifolds for robot motor control},
  booktitle = {Proc. 2007 IEEE International Conference on Robotics and Automation (ICRA 2007)},
  year = 2007,
}

@inproceedings{CTT100576252,
  author = {Hachiya, H. and Akiyama, T. and Sugiyama, M.},
  title = {Adaptive importance sampling with automatic model selection in value function approximation},
  booktitle = {IEICE Technical Report,NC2007-84,},
  year = 2007,
}

@inproceedings{CTT100581890,
  author = {Sugiyama, M. and Hachiya, H. and Towell, C. and Vijayakumar, S.},
  title = {Geodesic Gaussian kernels for value function approximation.},
  booktitle = {In Proceeding of 2006 Workshop on Information-Based Induction Science(IBIS2006)},
  year = 2006,
}