首页> 外文OA文献 >Existence of optimal stationary policies in discounted Markov decision processes: approaches by occupation measures

【2h】

Existence of optimal stationary policies in discounted Markov decision processes: approaches by occupation measures

机译：折扣马尔可夫决策过程中最优平稳策略的存在：职业测度的方法

代理获取

本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。

页面导航

著录项
引文网络
相似文献
相关主题

著录项

作者
Kurano M.; Kawai M.;
展开▼
作者单位

展开▼
年度 1994
总页数
原文格式 PDF
正文语种
中图分类

相似文献

外文文献
中文文献
专利

1. MONOTONE OPTIMAL POLICIES IN DISCOUNTED MARKOV DECISION PROCESSES WITH TRANSITION PROBABILITIES INDEPENDENT OF THE CURRENT STATE: EXISTENCE AND APPROXIMATION [J] . Rosa M. Flores-Hernandez Kybernetika . 2013,第5期

机译：具有独立于电流状态的转移概率的马尔可夫折扣决策过程中的单调最优策略：存在性和近似性
2. Monotone optimal policies in discounted Markov decision processes with transition probabilities independent of the current state: existence and approximation [J] . Flores-Hernández Rosa María Kybernetika . 2013,第5期

机译：折现马尔科夫决策过程中的单调最优策略，其转移概率与当前状态无关：存在和近似
3. Optimality of Quasi-Open-Loop Policies for Discounted Semi-Markov Decision Processes [J] . Adelman Daniel, Mancini Angelo J. Mathematics of operations research . 2016,第4期

机译：折扣半马尔可夫决策过程的拟开环策略的最优性
4. Approximate Robust Policy Iteration for Discounted Infinite-Horizon Markov Decision Processes with Uncertain Stationary Parametric Transition Matrices [C] . Baohua Li, Si, J. Neural Networks, The 2007 IEEE International Joint Conference on . 2007

机译：不确定平稳参数化转移矩阵的无穷折扣马尔可夫决策过程的近似鲁棒策略迭代
5. Markov Decision Processes and Approximate Dynamic Programming Methods for Optimal Treatment Design [D] . Mason, Jennifer Elizabeth 2012

机译：马尔可夫决策过程和近似动态规划方法进行最优处理设计
6. Evolving Robust Policy Coverage Sets in Multi-Objective Markov Decision Processes Through Intrinsically Motivated Self-Play [O] . Sherif Abdelfattah, Kathryn Kasmarik, Jiankun Hu 2018

机译：通过内在动机的自我博弈在多目标马尔可夫决策过程中发展稳健的政策覆盖范围
7. ON THE EXISTENCE OF AN OPTIMAL STATIONARY I-POLICY IN NON-DISCOUNTED MARKOVIAN DECISION PROCESSES WITH INCOMPLETE STATE INFORMATION [O] . Masami Kurano 1977

机译：在不完整状态信息的非折扣马尔可维亚决策过程中存在最佳静止I策略的存在
8. The Existence of Pure, Stationary Optimal Policies for a Class of Markov Renewal Programs [R] . Fox, B. 1966

机译：一类马尔可夫更新计划的纯，平稳最优策略的存在性

Existence of optimal stationary policies in discounted Markov decision processes: approaches by occupation measures

著录项

引文网络

相似文献

相关主题

期刊订阅