Delft_MountainCar-master
所属分类：人工智能/神经网络/深度学习
开发工具：matlab
文件大小：740KB
下载次数：10
上传日期：2020-01-02 14:11:32
上 传 者：
啊楠楠
说明： 在matlab实现强化学习中的Q学习算法，用于机器人走出房间的例子
(Implement Q learning algorithm in reinforcement learning in matlab for the example of a robot walking out of a room)
文件列表:
BuildActionList.m (157, 2019-03-29)
BuildQTable.m (282, 2019-03-29)
BuildRadialBasisCentres.m (750, 2019-03-29)
BuildRadialBasisWidth.m (283, 2019-03-29)
BuildStateList.m (502, 2019-03-29)
Demo.m (25, 2019-03-29)
DiscretizeState.m (195, 2019-03-29)
DoAction.m (945, 2019-03-29)
Episode.m (2141, 2019-03-29)
EpisodeRBF.m (1796, 2019-03-29)
EpsGreedyRBF.m (424, 2019-03-29)
GetBestAction.m (246, 2019-03-29)
GetBestActionRBF.m (477, 2019-03-29)
GetFeatureVector.m (848, 2019-03-29)
GetReward.m (487, 2019-03-29)
MountainCarDemo.m (2022, 2019-03-29)
MountainCarDemoRBF.m (3323, 2019-03-29)
MountainCarPlot.m (1029, 2019-03-29)
MountainCarPlotSingle.m (679, 2019-03-29)
NormaliseVector.m (521, 2019-03-29)
PrintStats.m (328, 2019-03-29)
PrintTheta.m (243, 2019-03-29)
UpdateSARSA.m (567, 2019-03-29)
UpdateTheta.m (522, 2019-03-29)
Winokan_RBFMountainCar.pdf (789736, 2019-03-29)
e_greedy_selection.m (335, 2019-03-29)
edist.m (110, 2019-03-29)
# Delft_MountainCar
- To run original discretised demo: ```MountainCarDemo(n_episodes)``` [int]
- To run adapted continuous demo: ```MountainCarDemoRBF(n_episodes,animate?)``` [int,bool]
近期下载者：
相关文件：
收藏者：