Fitted value function iteration with probability one contractions

Jeno Pal; John Stachurski

首页> 外文期刊>Journal of Economic Dynamics and Control >Fitted value function iteration with probability one contractions

【24h】

Fitted value function iteration with probability one contractions

机译：拟合值函数迭代概率为一收缩

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper studies a value function iteration algorithm based on nonexpanstve function approximation and Monte Carlo integration that can be applied to almost all stationary dynamic programming problems. The method can be represented using a randomized fitted Bellman operator and a corresponding algorithm that is shown to be globally convergent with probability one. When additional restrictions are imposed, an 0_P(n~(-1/2)) rate of convergence for Monte Carlo error is obtained.

机译：本文研究了一种基于非展开函数逼近和蒙特卡洛积分的值函数迭代算法，该算法可以应用于几乎所有平稳动态规划问题。可以使用随机拟合的Bellman算子和相应的算法表示该方法，该算法显示为以概率1全局收敛。当施加附加限制时，获得蒙特卡洛误差的0_P（n〜（-1/2））收敛速度。

著录项

来源
《Journal of Economic Dynamics and Control》 |2013年第1期|251-264|共14页
作者
Jeno Pal; John Stachurski;
展开▼
作者单位

Department of Economics, Central European University, Budapest, Hungary;

Research School of Economics, Australian National University, Canberra 0200, Australia;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
dynamic programming; value function iteration; monte carlo;

机译：动态编程值函数迭代;蒙特卡洛;

相似文献

外文文献
中文文献
专利

1. Invariant measures of Markov operators associated to iterated function systems consisting of phi-max-contractions with probabilities [J] . Georgescu Flavian, Miculescu Radu, Mihail Alexandru Indagationes Mathematicae . 2019,第1期

机译：与迭代函数系统相关联的马尔可夫运算符的不变措施，该函数系统与概率的PHI-Max-agregate组成
2. Iterated Function Systems Generated by Strict Contractions and Place-dependent Probabilities [J] . Radu Zaharopol Bulletin of the Polish Academy of Sciences. Mathematics . 2000,第4期

机译：严格收缩和位置相关概率生成的迭代函数系统
3. Linear Fitted-Q Iteration with Multiple Reward Functions [J] . Lizotte Daniel J., Bowling Michael, Murphy Susan A. Journal of machine learning research . 2012,第Nov期

机译：具有多个奖励函数的线性Fitd-Q迭代
4. Linear Fitted-Q Iteration with Multiple Reward Functions [C] . Daniel J. Lizotte, Michael Bowling, Susan A. Murphy Proceedings of the Twenty-Third International conference on Automated planning and Scheduling . 2013

机译：具有多个奖励函数的线性Fitd-Q迭代
5. THE H-FUNCTION AND PROBABILITY DENSITY FUNCTIONS OF CERTAIN ALGEBRAIC COMBINATIONS OF INDEPENDENT RANDOM VARIABLES WITH H-FUNCTION PROBABILITY DISTRIBUTIONS. [D] . COOK, IVY DEWEY, JR. 1981

机译：具有H函数概率分布的独立随机变量的某些代数组合的H函数和概率密度函数。
6. Linear Fitted-Q Iteration with Multiple Reward Functions [O] . Daniel J. Lizotte, Michael Bowling, Susan A. Murphy -1

机译：具有多个奖励功能的线性拟合Q迭代
7. Fitted Value Function Iteration With Probability One Contractions [O] . Jenö Pál, John Stachurski 100

机译：具有概率一次收缩的拟合值函数迭代
8. The H-Function and Probability Density Functions of Certain Algebraic Combinations of Independent Random Variables with H-Function Probability Distribution [R] . Cook, I. D. 1981

机译：具有H-函数概率分布的某些独立随机变量代数组合的H-函数和概率密度函数

Fitted value function iteration with probability one contractions

摘要

著录项

相似文献

相关主题

期刊订阅