arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1210.4887cs.LGcs.AIstat.ML
收藏

POMDPs的Hilbert空间嵌入

Hilbert Space Embeddings of POMDPs

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

摘要:

提出了一种POMDPs策略学习的非参数方法。该方法将状态、观测和动作的分布表示为特征空间中的嵌入,特征空间是再生核希尔伯特空间。通过将核贝叶斯规则应用于这些分布嵌入来获得给定观测值的状态分布。在状态特征空间上定义了策略和价值函数,从而得到了Bellman方程的特征空间表达式。然后,可以使用值迭代来估计最优价值函数和相关联的策略。实验结果证实,正确的政策学习使用的特征空间表示。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑