共查询到16条相似文献,搜索用时 78 毫秒
1.
2.
3.
应用Markov决策过程与性能势相结合的方法,给出了呼叫接入控制的策略优化算法。所得到的最优策略是状态相关的策略,与基于节点已占用带宽决定行动的策略相比,状态相关策略具有更好的性能值,而且该算法具有很快的收敛速度。 相似文献
4.
基于性能势理论和等价Markov过程方法,研究了一类半Markov决策过程(SMDP)在参数化随机平稳策略下的仿真优化算法,并简要分析了算法的收敛性.通过SMDP的等价Markov过程,定义了一个一致化Markov链,然后根据该一致化Markov链的单个样本轨道来估计SMDP的平均代价性能指标关于策略参数的梯度,以寻找最优(或次优)策略.文中给出的算法是利用神经元网络来逼近参数化随机平稳策略,以节省计算机内存,避免了“维数灾”问题,适合于解决大状态空间系统的性能优化问题.最后给出了一个仿真实例来说明算法的应用. 相似文献
5.
6.
7.
8.
9.
将稳健-容错辩识与突变检测技术相结合,在合理给出平稳过程位置一刻度参数容错辨识算法的基础上,构造了一组可靠实用的过程脉冲型故障在线检测与辨识算法,通过过程差分处理,将平稳过程阶跃突变转化为过程脉冲型突变,为利用脉冲型故障检测与辨识方法处理阶跃型突变问题建立了联系。仿真计算证实了所建立的检测与辨识算法的有效性。 相似文献
10.
11.
This paper deals with discrete-time Markov control processes with Borel state space, allowing unbounded costs and noncompact control sets. For these models, the existence of average optimal stationary policies has been recently established under very general assumptions, using an optimality inequality. Here we give a condition, which is a strengtened version of a variant of the ‘vanishing discount factor’ approach, for the optimality equation to hold. 相似文献
12.
We show the existence of average cost optimal stationary policies for Markov control processes with Borel state space and unbounded costs per stage, under a set of assumptions recently introduced by L.I. Sennott (1989) for control processes with countable state space and finite control sets. 相似文献
13.
The paper discusses the robustness of discrete-time Markov control processes whose transition probabilities are known up to certain degree of accuracy. Upper bounds of increase of a discounted cost are derived when using an optimal control policy of the approximating process in order to control the original one. Bounds are given in terms of weighted total variation distance between transition probabilities. They hold for processes on Borel spaces with unbounded one-stage costs functions. 相似文献
14.
This communique provides an exact iterative search algorithm for the NP-hard problem of obtaining an optimal feasible stationary Markovian pure policy that achieves the maximum value averaged over an initial state distribution in finite constrained Markov decision processes. It is based on a novel characterization of the entire feasible policy space and takes the spirit of policy iteration (PI) in that a sequence of monotonically improving feasible policies is generated and converges to an optimal policy in iterations of the size of the policy space at the worst case. Unlike PI, an unconstrained MDP needs to be solved at iterations involved with feasible policies and the current best policy improves all feasible policies included in the union of the policy spaces associated with the unconstrained MDPs. 相似文献
15.
平均和折扣准则MDP基于TD(0)学习的统一NDP方法 总被引:3,自引:0,他引:3
为适应实际大规模M arkov系统的需要,讨论M arkov决策过程(MDP)基于仿真的学习优化问题.根据定义式,建立性能势在平均和折扣性能准则下统一的即时差分公式,并利用一个神经元网络来表示性能势的估计值,导出参数TD(0)学习公式和算法,进行逼近策略评估;然后,根据性能势的逼近值,通过逼近策略迭代来实现两种准则下统一的神经元动态规划(neuro-dynam ic programm ing,NDP)优化方法.研究结果适用于半M arkov决策过程,并通过一个数值例子,说明了文中的神经元策略迭代算法对两种准则都适用,验证了平均问题是折扣问题当折扣因子趋近于零时的极限情况. 相似文献
16.
在智能规划问题上,寻找规划解都是NP甚至NP完全问题,如果动作的执行效果带有不确定性,如在Markov决策过程的规划问题中,规划的求解将会更加困难,现有的Markov决策过程的规划算法往往用一个整体状态节点来描述某个动作的实际执行效果,试图回避状态内部的复杂性,而现实中的大量动作往往都会产生多个命题效果,对应多个命题节点。为了能够处理和解决这个问题,提出了映像动作,映像路节和映像规划图等概念,并在其基础上提出了Markov决策过程的蚁群规划算法,从而解决了这一问题。并且证明了算法得到的解,即使在不确定的执行环境下,也具有不低于一定概率的可靠性。 相似文献