搜索资源列表
TankWar6
- 强化学习版坦克大战,利用Q学习来完成坦克大战,体现强化学习的基本原理。-Battle City version of reinforcement learning, the use of Q-learning to accomplish physics, reflecting strengthening basic principles of learning.
reinforementlearning11
- 关于强化学习必不可少的论文,讲的很详细,希望对大家学习有利。-Papers about reinforcement learning is indispensable, very detailed, hope is good for everybody to learn
Q-Learning
- Q 学习方面的MATLAB程序,对于研究强化学习和自适应动态规划的朋友很有参考价值-Q learning MATLAB. For the study of reinforcement learning and adaptive dynamic programming
maze
- 经典的迷宫问题 可用于对强化学习最优路径的研究-The classic maze can be used to study the optimal path reinforcement learning
salamander
- webots 强化学习 避障算法 惩罚 随机 -webots punishment reinforcement learning obstacle avoidance algorithm randomly
Kernel-Reinforcement-Learning
- 基于核函数方法的强化学习算法,用于处理连续状态空间问题或者大规模离散状态空间问题-Kernel-based reinforcement learning algorithm method for handling large-scale continuous state space problem or discrete state space problem
RL-in-Multi-Continuous-Action-Spaces
- 机器学习,大规模连续行为空间的强化学习算法研究及其应用分析-Machine learning, large-scale study of reinforcement learning algorithm continuously analyzes the behavior of space and its applications
Reinforcement--Transfer-Learning
- 采用迁移的方法来处理强化学习中策略空间的搜索问题-Migration method is adopted to deal with reinforcement learning strategy in the space of the search problem
mtncarMatlab
- 这是一个实现强化学习的代码,可以解决山地车问题。解压文件,运行main.m可以出现一个带有按钮的窗口。-This is a matlab code for reinforcement learning for solving the mountain car problem. Untar the file and run the main.m file, then it brings up a window with all the d
FAReinforcement_V21
- 强化学习的matlab实现,希望对家有用-Reinforcement learning matlab, I hope to be useful at home
Reinforcement-Learning
- 斯坦福大学NG教授的用强化学习控制无人机的文章-Stanford university professor NG with reinforcement learning control of unmanned aerial vehicle (uav)
flappybird-qlearning-bot
- 基于深度强化学习的Flappy Bird机器人-Flappy Bird Bot using Reinforcement Learning
inverted-pendulum-control
- 利用强化学习的自适应动态规划中的值迭代和策略迭代方法,神经网络控制方法,LQR状态调节器最优控制方法,实现了三维倒立摆在飞行器上的稳定控制。鲁棒性很强,进行了高斯白噪声的扰动实验。-Reinforcement learning adaptive dynamic programming in value iteration and policy iteration method, neural network control method
bayesian-learning
- 贝叶斯学习和强化学习相结合,其中包含贝叶斯Q学习-bayesian learning combined with reinforcement learning
matlab-QLEARNING
- 模拟机器人路径规划,采用强化学习中的Q学习算法来实现,最后会返回机器人选择路径的坐标位置-code for path searching
ReinforcementLearning
- 里面有个例子供大家参考。关于强化学习,希望共同学习共同进步。-Reinforcement Learning
irl_toolkit
- 逆向强化学习很有用的代码,对学习很有帮助,推荐使用-inverse reinforcements learning
Q-Learning-Example-1
- Q-学习是一种重要的强化学习方法,提供一个Q-学习做路径规划的例子,初学者可以通过代码学习Q-学习的原理。-Q- learning is an important reinforcement learning methods, to provide an example of Q- learning to do path planning, beginners can learn the principles of Q- code.
MATLAB
- 时序差分学习是强化学习的一种重要算法,该代码提供了时序差分学习做路径规划的一个仿真。-Temporal difference learning is an important algorithm for reinforcement learning, which provides a simulation of sequential differential learning for path planning.
Reinforcement-Learning
- 基于神经网络的强化学习是对强化学习算法的一种改进,本文讲述了将基于神经网络的强化学习算法用于移动机器人动态导航。-Reinforcement learning based on neural network is an improvement of reinforcement learning algorithm. This paper describes the reinforcement learning algorithm bas