The Institute of Statistical Mathematics(统计数理研究所);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Gatsby Computational Neuroscience Unit, CSML, UCL(盖茨比计算神经科学单元,CSML,伦敦大学学院)
Yu Nishiyama, Abdeslam Boularias, Arthur Gretton, Kenji Fukumizu
备注:
Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)
A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces. Distributions over states given the observations are obtained by applying the kernel Bayes' rule to these distribution embeddings. Policies and value functions are defined on the feature space over states, which leads to a feature space expression for the Bellman equation. Value iteration may then be used to estimate the optimal value function and associated policy. Experimental results confirm that the correct policy is learned using the feature space representation.
Reproducing kernel Hilbert C*-module and kernel mean embeddings
NTT Network Service Systems Laboratories, NTT Corporation(NTT网络服务系统实验室,NTT公司);Graduate School of Science and Technology, Keio University(庆应义塾大学科学与技术研究生院);Center for Data Science, Ehime University(爱媛大学数据科学中心);Center for Advanced Intelligence Project, RIKEN(理化学研究所高级智能项目中心);Faculty of Science and Technology, Keio University(庆应义塾大学科学与技术学部)
Kernel Mean Embedding of Distributions: A Review and Beyond
Mahidol University(玛希隆大学);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Institute of Statistical Mathematics(统计数学研究所);Pennsylvania State University(宾夕法尼亚州立大学)
University of Alberta(阿尔伯塔大学);Charles University(查理大学);EquiLibre Technologies, Inc.(EquiLibre科技公司);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所)
Vector-Valued Distributional Reinforcement Learning Policy Evaluation: A Hilbert Space Embedding Approach
Department of Statistics, University of Illinois Urbana-Champaign(统计系,伊利诺伊大学厄巴纳-香槟分校);Department of Bioinformatics and Biostatistics, University of Louisville(生物信息学与生物统计学系,路易斯维尔大学)
Addressing Dynamic and Sparse Qualitative Data: A Hilbert Space Embedding of Categorical Variables
Samuel Curtis Johnson Graduate School of Management(塞缪尔·柯蒂斯·约翰逊管理研究生院);Cornell University(康奈尔大学);Lee Kong Chian School of Business(李光前商学院);Singapore Management University(新加坡管理大学)
Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
Universidad Rey Juan Carlos(胡安卡洛斯国王大学);Centro de Investigación for Data, Complex Networks and Cybersecurity Sciences, Universidad Rey Juan Carlos(胡安卡洛斯国王大学数据、复杂网络与网络安全科学研究中心)