搜索资源列表
BinwaveletImageEnhancement
- 学习二进小波变换用于图像增强，很好的例子，可以实现非线性增强。希望对大家有帮助。-study wavelet transform for image enhancement, good example, can achieve a nonlinear increase. We want to help.
Qlearning算法
- 关于增强学习的一个例子，Q-learning算法，和大家分享。-An example of reinforcement learning, and to share.
Q-learning
- 关于增强学习的一个例子，Q-learning算法，和大家分享。-An example of reinforcement learning, and to share.
SARSA
- 增强式学习示例，和大家分享，希望能对大家有帮助。-Reinforcement learning example, to share, hope you can help.
ReinforcementLearning
- 增强学习Matlab源吗,对机器学习,在线控制的人有所帮助-Matlab source you enhance the learning of machine learning, online help people control
thinkpad
- 本人原创的一个人和电脑互取苹果的游戏程序，核心是Fibonacci数列，供学习c/c++和数据结构的新手学习，以增强学习兴趣和热情。-I have an original and Apple computers and take the game procedures, the core is the Fibonacci series for learning c/c++ and data structure of new learning, to enhance the interest an
multiboost-0.61.src.tar
- Adaboost实现，主要用于机器学习的多分类器聚合， 最终形成分类效果逐渐增强的分类器-Adaboost implementation, is mainly used for machine learning, multiple classifier aggregation, the final shape classification results show a gradual increase of the classifier
TimeSeriesPredictionUsingSupportVectorRegressionNe
- 为了选择神经网络的最好结构以及增强模型的推广能力，提出一种自适应支持向量回归神经网络(SVR—NN)。SVR—NN 用支持向量回归(SVR)方法获得网络的初始结构和权值， 白适应地生 成网络隐层结点，然后用基于退火过程的鲁棒学习算法更新网络结点疹教和权 主。 SVR—NN有很 好的收敛性和鲁棒性，能抑制由于数据异常和参数选择不当所导致的“过拟合，’现象。将SVR—NN 应用到时间序列预测上。结果表明，SVR．NN预测模型能精确地预测混沌时间序列，具有很好的 理论和应用价值。-Ab
machine-learningPPT
- 书中主要涵盖了目前机器学习中各种最实用的理论和算法，包括概念学习、决策树、神经网络、贝叶斯学习、基于实例的学习、遗传算法、规则学习、基于解释的学习和增强学习等-The book mainly covers the current variety of the most practical machine learning theory and algorithms, including the concept of learning, decision trees, neural network
multiagent_q_learning
- 多用户环境中，增强学习算法仿真实验，特别是多用户Q学习算法的应用-In multi-agent scenarios, this package provides a very good simulation tool for multi-agent Q-learning algorithm.
KLSPI-Algorithm-theory
- 基于核函数的增强学习算法的理论分析与算法描述，及其在反馈控制上的应用-Based on theoretical analysis and descr iption of reinforcement learning algorithm kernel function, and its application in the feedback control
rlcpp
- 增强学习部分算法的c++实现（sarsa、Q-learning、QV-learning）-reinforcement learning by c++
ReinforcementLearning
- 增强学习的一个代码实例，希望对初学者有些作用，代码简单易懂，还附有注释。-Enhance learning code examples for beginners hope some effect, the code is simple to understand, but also with comments.
Q-Learing-path-planning-MATLAB
- 基于增强学习Q-learning方法的路径规划matlab仿真程序-Based on the enhanced learning Q-learning method of path planning matlab simulation program
sourceCode
- 用python 语言结合DNN简单实现语音增强(DNN speech enhancement)
Q学习
- 增强学习(Q-learning)要解决的是这样的问题:一个能感知环境的自治agent，怎样通过学习选择能达到其目标的最优动作(Reinforcement learning (Q-learning) has to solve this problem: an autonomous agent that can perceive the environment, and how to achieve the optimal action of its target through learning
dcgan_mnist（对抗学习）
- 对抗学习，也有叫“增强学习”。其原理是机器自己与自己进行对抗或博弈，更通俗点说，就是机器人与机器人下棋。("Against learning", also called "enhanced learning". The principle is that the machine itself is playing against or playing games with itself, and more generally speaking, it is
CS294
- 机器学习文档，CS294主要讲深度增强学习，课程实例很多，相信对学习有所帮助。(Machine Learning,Mainly speaking of deep reinforcement learning,,many examples of courses,I believe that learning helps.)
matlab Q学习仿真
- 基于Q学习算法，寻找最优路径，是强化学习中的一种，很实用，代码很详细，有备注(Searching for the optimal path based on Q algorithm is a kind of reinforcement learning. It is very practical, the code is very detailed, with notes.)
重要-SARSA
- 强化学习的一种，基于sarsa算法，寻找最优路径，可运行(One kind of reinforcement learning, based on sarsa algorithm, seeks the optimal path, which can run)