A　State　Space　Compression　Method　Based　on　Multivariate　Analysis　for　Reinforcement　Learning　in　High-dimensional　Continuous　State　Spaces

スポンサーリンク

概要

• 論文の詳細を見る

• A state space compression method based on multivariate analysis was developed and applied to reinforcement learning for high-dimensional continuous state spaces. First, useful components in the state variables of an environment are extracted and meaningless ones are removed by using multiple regression analysis. Next, the state space of the environment is compressed by using principal component analysis so that only a few principal components can express the dynamics of the environment. Then, a basis of a feature space for function approximation is constructed based on orthonormal bases of the important principal components. A feature space is thus autonomously construct without preliminary knowledge of the environment, and the environment is effectively expressed in the feature space. An example synchronization problem for multiple logistic maps was solved using this method, demonstrating that it solves the curse of dimensionality and exhibits high performance without suffering from disturbance states.

• 一般社団法人電子情報通信学会の論文
• 2006-08-01

著者

• 佐藤 仁樹

  Future University-Hakodate

関連論文

• Approximation and Analysis of Non-linear Equations in a Moment Vector Space(Nonlinear Problems)
• Analysis Based on Moment Vector Equation for Interacting Identical Elements with Nonlinear Dynamics
• Global Nonlinear Optimization Based on Wave Function and Wave Coefficient Equation
• A　State　Space　Compression　Method　Based　on　Multivariate　Analysis　for　Reinforcement　Learning　in　High-dimensional　Continuous　State　Spaces
• Reinforcement　Learning　with　Orthonormal　Basis　Adaptation　Based　on　Activity-Oriented　Index　Allocation

スポンサーリンク