Qlearningcar

所属分类:matlab编程
开发工具:matlab
文件大小:12KB
下载次数:548
上传日期:2010-05-20 20:30:10
上 传 者better1234
说明:  Simulink 控制VR环境中的小车。小车有5个距离传感器,能够慢慢学会避开墙壁和障碍物。小车采用加强学习(Q learning),采用神经网络对Q函数逼近。由于使用了模拟退火,小车在开始的时候会经常撞击障碍物,10次后基本就不会再撞了。 小车的外观模型使用了"w198406141"在本论坛的虚拟现实区发布的VR模型。
(VR environment Simulink control car. There are 5 car distance sensor, can gradually learn to avoid walls and obstacles. Car used to enhance learning (Q learning), using neural networks Q function approximation. As the use of simulated annealing, the car will start when the regular crash barrier, 10 times the fundamental will no longer hit. The appearance model used car " w198406141" in this forum area of virtual reality VR model release.)

文件列表:
QlearningCar.wrl (18184, 2010-04-16)
qlearningcar.mdl (35405, 2010-04-16)

近期下载者

相关文件


收藏者