资源分类
》 资源 》论文》The Infinite Regionalized Policy Representation

The Infinite Regionalized Policy Representation

2020-02-27 | |  47 |   38 |   0

Abstract

We introduce the infinite regionalized policy presentation (iRPR), as a nonparametric policy for reinforcement learning in partially observable Markov decision processes (POMDPs). The iRPR assumes an unbounded set of decision states a priori, and infers the number of states to represent the policy given the experiences. We propose algorithms for learning the number of decision states while maintaining a proper balance between exploration and exploitation. Convergence analysis is provided, along with performance evaluations on benchmark problems.

上一篇：Learning Output Kernels with Block Coordinate Descent

下一篇：On Bayesian PCA: Automatic Dimensionality Selection and Analytic Solution

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...