登录
首页 » Python » cartpole-qlearning-master

cartpole-qlearning-master

于 2021-04-29 发布
0 229
下载积分: 1 下载次数: 2

代码说明:

说明:  深度强化学习DQN在倒立摆上的实现,python代码,使用torch,gym库(Implementation of deep reinforcement learning dqn on inverted pendulum)

文件列表:

cartpole-qlearning-master, 0 , 2019-12-19
cartpole-qlearning-master\.gitignore, 31 , 2019-12-19
cartpole-qlearning-master\LICENSE.md, 1072 , 2019-12-19
cartpole-qlearning-master\README.md, 526 , 2019-12-19
cartpole-qlearning-master\cartpole_qlearning, 0 , 2019-12-19
cartpole-qlearning-master\cartpole_qlearning\__init__.py, 0 , 2019-12-19
cartpole-qlearning-master\cartpole_qlearning\agent.py, 841 , 2019-12-19
cartpole-qlearning-master\cartpole_qlearning\main.py, 2524 , 2019-12-19
cartpole-qlearning-master\requirements.txt, 144 , 2019-12-19

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • MMC.voice
    This is the design of a application which drive an AVR mcu to record and broadcast WAV voice stored in an Memory card.
    2012-05-17 03:32:40下载
    积分:1
  • 800X600真彩色源代码
    说明:  石器时代大屏真彩色源代码,支持32位大屏,包含sever和客户端dll(c++ origin code include server and client)
    2021-04-24 12:38:47下载
    积分:1
  • Code
    说明:  Actor.m为动作网络的类 ANN.m为神经网络的类 cartpole_model.m为控制模型 Critic.m为评价网络的类 Layer为神经层 main为主函数(Actor. M is a class of Action Network Ann. M is a kind of neural network Cartpole? Model. M is the control model Critical. M is a class of evaluation network Layer is neural layer Main is the main function)
    2019-11-28 16:21:51下载
    积分:1
  • ansys程序
    ansys骨料生成,用于球形随机骨料的产生。用于混凝土和沥青分析(The ANSYS aggregate is generated for the production of spherical random aggregate. Analysis of concrete and asphalt)
    2020-10-27 21:39:58下载
    积分:1
  • reactionrate
    说明:  fluent表面反应udf文件,基于Langmuir机理的反应速率设置(Fluent Surface Reaction UDF File, Reaction Rate Setting Based on Langmuir Mechanism)
    2020-11-07 15:49:50下载
    积分:1
  • 粒子群算法试算
    说明:  粒子群算法,也称粒子群优化算法(Particle Swarm Optimization),缩写为 PSO, 是近年来发展起来的一种新的进化算法(Evolutionary Algorithm - EA)。PSO 算法属于进化算法的一种,和模拟退火算法相似,它也是从随机解出发,通过迭代寻找最优解,它也是通过适应度来评价解的品质,但它比遗传算法规则更为简单,它没有遗传算法的“交叉”(Crossover) 和“变异”(Mutation) 操作,它通过追随当前搜索到的最优值来寻找全局最优。这种算法以其实现容易、精度高、收敛快等优点引起了学术界的重视,并且在解决实际问题中展示了其优越性。粒子群算法是一种并行算法。(Particle swarm optimization (PSO), also called particle swarm optimization (Particle Swarm Optimization), is abbreviated as PSO, which is a new evolutionary algorithm (Evolutionary Algorithm EA) developed in recent years. PSO algorithm is a kind of evolutionary algorithm. It is similar to simulated annealing algorithm. It also starts from the random solution and finds the optimal solution by iteration. It also evaluates the quality of the solution through fitness, but it is simpler than the genetic algorithm rule. It does not have the crossover (Crossover) and the Mutation operation of genetic algorithm. Search for global optimum. This algorithm has attracted the attention of the academic community for its advantages of easy realization, high accuracy and fast convergence, and has shown its superiority in solving practical problems. Particle swarm optimization (PSO) is a parallel algorithm.)
    2018-12-25 14:28:52下载
    积分:1
  • 预测控制是适用于含有大滞后环节、积分环节的复杂工业系统控制。GPC为广义预测控制...
    预测控制是适用于含有大滞后环节、积分环节的复杂工业系统控制。GPC为广义预测控制-predictive control is applicable to lag links with big, integral part of the complex industrial control systems. GPC for GPC
    2022-08-12 19:13:56下载
    积分:1
  • 并行算法,矩阵相乘,MPI。 cannon.c
    并行算法,矩阵相乘,MPI。 cannon.c-MPI,MUTPLAY cannon.c
    2022-05-21 07:31:06下载
    积分:1
  • gold_generator
    扩频通信常用的 gold序列生成matlab m文件 希望对大家有点帮助(Commonly used spread spectrum communication gold sequence matlab m file to generate hope for all of us a little help)
    2020-07-02 22:00:01下载
    积分:1
  • 《MATLAB 神经网络43个案例分析》源代码&数据
    说明:  《MATLAB 神经网络43个案例分析》源代码&数据(Source code & data of 43 cases analysis of MATLAB neural network)
    2020-06-06 22:15:25下载
    积分:1
  • 696516资源总数
  • 106914会员总数
  • 0今日下载