搜索资源列表
MDP-model-of-MPNP
- 在matlab平台上，针对多周期报童问题，采用值迭代算法、策略迭代算法和强化学习算法求解MDP模型的实例-This is an example presentting how to apply value-iteration algorithm，policy-iteration algorithm and reinforcement learning algorithm to MDP model, which aims to solve
Downloads
- 两段强化学习算法，提供给研究算法的同学。不知道有没有用-The two reinforcement learning algorithms, to provide students to study algorithm. Do not know that there is no use
mdp-q
- 强化学习的谱聚类算法，实现基于图割的状态聚类-Reinforcement Learning spectral clustering algorithm to achieve the state of clustering based on graph cuts
RLtoolkit
- 强化学习的仿真程序，用来实现小车爬坡的强化学习，有图形化的表达-Reinforcement learning simulation program used to implement the car climbing reinforcement learning, the graphical expression of
MDP
- 马尔科夫决策过程，强化学习的一种算法。主要用于机器人。-Markov process decision
Diversity-density-learning-algorithm
- 多示例学习是与监督学习、非监督学习和强化学习并列的第四类学习框架-Multi-instance learning with supervised learning, unsupervised learning and strengthen the learning parallel learning fr a mework
Q-learning_pendulum
- 采用强化学习算法对倒立摆的摆动过程进行学习，通过学习使其保持平衡状态-Reinforcement learning algorithm to learn the inverted pendulum swing process, by learning to balance state
ai-robot
- 机器人人论文，强化学习，环境建立，仿人机器人等方向-Papers of robot people, strengthen the learning environment to establish a humanoid robot direction
Mmutti-agentsu
- 多智能体工具包，可直接用来进行行多智能体强化学习算法设计与仿真 -Multi-agent toolkit, can be directly used for design and simulation of the line multi-agent reinforcement learning algorithm
A-good-learning-Q-source-
- Q-Learning强化学习的代码实现.rar-A good learning Q source code, for learning has a great role in reinforcement learning
image-study
- 多示例学习是与监督学习、非监督学习和强化学习并列的第四类学习框架，目前已广泛应用于药物设计、图像搜索等领域,并已获得很好的效果。在多示例学习中，训练样本是由多个示例组成的包，包是有概念标记的，但示例本身却没有概念标记，学习的目的是预测新包的类别。-Multi-instance learning and supervised learning, unsupervised learning and reinforcement learnin
123
- 强化学习在数据中心资源节能管理中的研究，非常实用也比较新颖-Reinforcement Learning research in energy-saving management of data center resources
Renforce
- 强化学习的MATLAB简单实例程序，供机器学习的初学者参考使用。-Reinforcement Learning simple instance of MATLAB program for machine learning beginners use and reference.
MobileRobotSimQ
- 使用Q学习的一种强化学习算法，针对路径规划问题，用Q学习的方法解决-A method to solve planning the path, using Q_study, one method of reforence study.
inverted_pendulum_refernce_study
- 一种结合神经网络来控制倒立摆稳定的程序。用强化学习方法，训练两个网络，一个是行为网络，一个是评估网络-a method to balance a inverted pendulum, using reference studing, as well as neural network.
CSPSaQ-learningamatlab
- 基于强化学习的CSPS生产线优化设计，matlab源代码-Optimal design based on reinforcement learning the CSPS production line
2010-08-04_marl-1.3
- 基于强化学习与最优自适应控制器的智能机器人控制器-Based on reinforcement learning and optimal adaptive controller intelligent robot controller
ganzhiqisuanfa
- 介绍感知器学习算法及其变种，给出各种感知器算法的伪代码，指出各种算法的优点。给出感知器算法在线性可分和线性不可分 情况下的误差界定理，讨论各种感知器学习算法的误差界理论，给出各种算法的误差界。介绍感知器学习算法在在线优化场景、强化学习 场景和*机算法中的应用，并对未解决的问题进行讨论。-The perceptron learning algorithm and its variants, pseudo code is give
UntitledGG
- 一种强化学习的编码 自己做的 这方面国外研究很多 国内基本没有 大家多交流-An intensive study of coding to do their own research in this area, many domestic foreign exchange basically no everyone
HCGreedy
- 一种贪婪算法编码，可用于各种强化学习的实现中。-Encoding a greedy algorithm can be used to achieve a variety of reinforcement learning.