搜索资源列表
OpenAI
- 建立universe，为AI提供强化学习环境。- U5EFA u7AF u5883 u326
migong
- 使用Qlearing实现基本的走迷宫游戏(Using Qlearing to achieve maze game)
Improving wet clutch engagement with
- 将强化学习方法应用到离合器的接合控制，旨在获得快速平稳的接合，伴随着较小的转矩损失。(A common approach when applying reinforcement learning to address control problems is that of first learning a policy based on an approximated model of the plant, whose behavior can be quickly and safely exp
code
- 强化学习机器人自主导航模拟程序，应用了SARSA算法(reinforcement learning for self-navigating robot)
Model
- 倒立摆matlab模型，用于神经网络学习，强化学习等建模(matlab model for inverted pendulum)
自平衡机器人
- 基于强化学习的自平衡机器人（操作条件反射）(reinforcement learning robot)
reinforcement learning
- introduction to reinforcemnt learning
蒙特卡洛
- 蒙特卡洛算法是强化学习的一种算法，也是一种概率算法(The Monte Carlo algorithm is an algorithm for reinforcement learning)
1709.04326
- 多智能体设置在机器学习中的重要性日益突出。超过了最近的大量关于深度的工作多agent强化学习，层次强化学习，生成对抗网络和分散优化都可以看作是这种设置的实例。然而，多学习代理人的存在这些设置使得培训问题的非平稳常常导致不稳定的训练或不想要的最终结果。我们提出学习与对手的学习意识（萝拉），一种方法，原因的预期。其他代理的学习。罗拉学习规则包括一个额外的术语，解释了在预期的参数更新的代理政策其他药物。我们发现，利用似然比策略梯度更新的方法，可以有效地计算萝拉更新规则，使该方法适合于无模型强化学习。这
Machine_Learning_For_Control_Systems-master
- 实现倒立摆平衡的控制仿真，及其方便，matlab非常易懂(Realize the balance of inverted pendulum control simulation, and its convenience, Matlab is very easy to understand)
Lewis
- 本书是lewis 的一本强化学习专著，全英版，值得参考学习，pdf格式。(REINFORCEMENT LEARNING AND APPROXIMATE DYNAMIC PROGRAMMING FOR FEEDBACK CONTROL)
reinforement.tar
- 强化学习grid python代码，使用的算法为动态规划，很好的入门强化学习的例子(reinforement grid study.)
qianghuazhiyi1
- 对于强化学习中的特例算法Q学习，进行编程，通过编程，理解其的工作机制(For intensive learning, a special case algorithm Q learning, programming, through programming, to understand its working mechanism)
qianghuazhi3
- 讲解强化学习之3，通过强化学习之3的实例，更加理解强化学习的原理(To explain the 3 of intensive learning and to understand the principle of intensive learning by strengthening the 3 examples of learning)
qianghuazhi4
- q强化学习之4，通过具体的仿真实例讲解强化学习的原理(Q intensive learning 4, explain the principle of reinforcement learning through specific simulation examples)
qianghuazhi5
- 强化学习之5讲解强化学习的工作原理，通过编程实现(Strengthening the 5 explanation of the working principle of intensive learning by programming)
qianguazhi6
- jiangjie强化学习的原理，通过仿真更能理解什么是强化学习(Jiangjie the principle of strengthening learning, through simulation, more understanding of what is intensive learning)
最优控制
- 此程序利用强化学习的方法实现小车的最优控制。(Optimal control of car)
RL
- 用python搭建了各类常用的强化学习算法的框架，通过迷宫寻路的例子实现各类算法。(The framework of all kinds of commonly used reinforcement learning algorithms is built with Python, and all kinds of algorithms are realized by the example of labyrinth finding.)
Chapter 5 (Monte Carlo Methods)
- 讲解强化学习的基本思想，同时通过实例分析怎样编写强化学习(Explain the basic ideas of intensive learning and how to write intensive learning through an example.)