搜索资源列表
Chapter 6 (Temporal Difference Learning)
- 讲解强化学习中的Q学习和sarsa学习，并通过具体实例讲解怎样运用这些学习方法(Explain Q learning and sarsa learning in intensive learning, and explain how to use these learning methods through concrete examples)
c_netwebhxbc
- .NET编程源码，以供学习参考查阅。强化学习效果(.NET programming source for learning reference.)
reforce
- 强化学习的Q学习，关于强化学习的应用和算法，有很好的思路，可以从中举一反三，从而解决自己的问题，希望对大家能有所帮助(To strengthen the study of Q learning and to strengthen the application and algorithm of learning, we have a good idea. We can take one counter three from the middle and solve their own probl
tf-adnet-tracking-master
- 基于强化学习深度学习用于单目标跟踪算法的源码(Based on reinforcement learning, deep learning is used for single target tracking algorithm.)
qlearning4k-master
- qlearning4k是强化学习Python深度学习lib库Keras插件。它简单，是快速成型的理想选择。(Qlearning4k is a reinforcement learning add-on for the python deep learning library Keras. Its simple, and is ideal for rapid prototyping.)
蒙特卡罗算法与matlab(精品教程)
- 蒙特卡洛算法也常用于机器学习，特别是强化学习的算法中。一般情况下，针对得到的样本数据集建立相对模糊的模型，通过蒙特卡洛方法对于模型中的参数进行选取，使之于原始数据的残差尽可能的小。从而达到建立模型拟合样本的目的。(Monte Carlo algorithm is also commonly used in machine learning, especially in reinforcement learning algorithm. In general, a relatively fuzzy
ddpg
- 深度强化学习中DDPG算法的代码，用Python语言实现(The code of DDPG algorithm in deep reinforcement learning, implemented in Python language)
DDPG-Keras-Torcs-master
- 基于keras框架的强化学习代码，主要实现的是DDPG算法的代码，用keras框架实现(Reinforced learning code based on keras framework)
code
- Q-learning 算法实现AGV的最优路径规划，实测效果非常好，对于研究深度学习和强化学习的同学很有帮助！(The Q-learning algorithm realizes the optimal path planning of AGV, and the measured results are very good. It is very helpful for students who are studying deep learning and reinforcement learn
MAgent-master
- 多智能体的一段代码，有关强化学习，机器学习，很实用的一段代码！(A code of multi-agent, about reinforcement learning, machine learning, a very practical piece of code!)
mtncarMatlab
- 强化学习qlearning编写，回归算法规划轨迹(Reinforcement learning qlearning, return algorithm to plan trajectory)
10_7_gridworld_sarsa
- 通过最基础的实例来了解sarsa算法原理及应用(Understand the principle and application of sarsa algorithm through the most basic example.)
RL
- 强化学习 DQN代码，和通信相关，利用python进行训练，大家可以看看(reinforcement learning)
pytorch-a2c-ppo-acktr-master
- 改代码为ACKTR代码，该算法比传统的TRPO和DQN在运行速度和计算量都有很大的提升(scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation)
单一任务导航
- 测试深度马尔可夫决策来导航,给出了python的实现代码(MDP based navigation)
Averaged-DQN_ Variance Reduction and Stabilization for Deep Reinforcement Learning
- Averaged-DQN论文，关于强化学习领域的文章。
Q_Learning
- 实现强化学习交通配时，选取最优的配时方案(To realize the reinforcement learning traffic timing, the optimal timing scheme is selected)
qlearning
- 利用栅格法建模，基于强化学习Qlearning算法实现路径规划，可以实时显示(Using raster method to model and Qlearning algorithm based on reinforcement learning to realize path planning, it can be displayed in real time.)
Python核心编程入门必备强化葵花宝典
- python入门教学，案例示范，语言学习(python for beginners)
Dyna-H
- 设定动态仿真环境，环境为动态随机游戏，用于寻找最优路径(Use to find the optimal path)