-
WindyGridWorldQLearning
Q-learning (Watkins, 1989) is a simple way for agents to learn how to act optimally in controlled Markovian
domains. It amounts to an incremental method for dynamic programming which imposes limited computational
demands. It works by successively improving its evaluations of the quality of particular actions at particular states.
This paper presents and proves in detail a convergence theorem for Q,-learning based on that outlined in Watkins
(1989). We show that Q-learning converges to the optimum action-values with probability 1 so long as all actions
are repeatedly sampled in all states and the action-values are represented discretely. We also sketch extensions
to the cases of non-discounted, but absorbing, Markov environments, and where many Q values can be changed
each iteration, rather than just one.
- 2013-04-19 14:23:35下载
- 积分：1
-
indnmachinemodel_VHZ
matrix converter.....it is ac to ac convertor,......
- 2012-02-08 16:46:16下载
- 积分：1
-
prim
用matlab语言编写的最小生成树的prim算法的通用源程序。(Using matlab language prim)
- 2008-05-27 20:01:08下载
- 积分：1
-
Mutation_of_the_PSO
引入变异算子的PSO，希望对大家的学习研究有所帮助。(Mutation of the PSO, we hope to help the study of learning.)
- 2010-05-07 08:14:08下载
- 积分：1
-
9527
exercise1:为基于小波变化与局部能量的图像融合方法
exercise2:为基于自适应算法的图像融合算法
myfunction1~myfunction5:为性能指标评价函数(exercise1: To change and local energy based on wavelet image fusion method exercise2: adaptive algorithm based image fusion algorithm myfunction1 ~ myfunction5: performance indicators for the evaluation function)
- 2011-05-08 11:15:00下载
- 积分：1
-
metlab_excerise_50
metlab入门比做的50到题，很经典，大家如果想学的，静下心来好好看看。很不错。(metlab entry talks as that of the 50, classic, If you want to learn, reflecting back a good look. Is pretty good.)
- 2006-11-02 01:55:44下载
- 积分：1
-
MSR_FFT
MSR FFT for fast analysis
- 2010-11-11 18:33:05下载
- 积分：1
-
anttttsp
ant colony optamisation algo simulation for tsp...
- 2011-07-06 02:05:13下载
- 积分：1
-
Invertedpendulum
在分析的基础上，采用状态反馈控制中极点配置法设计了用于直线型一级倒立摆系统的控制器(On the basis of analysis,this procedure presents a Controller for linear 1-stage inverted pendulum system.Use MATLAB to simulate and certificate it)
- 2010-10-17 20:36:27下载
- 积分：1
-
sift
SIFT (scale invariant feature transform)
- 2010-10-28 19:44:14下载
- 积分：1
|
联系客服（QQ：3324461878）
