1 Star 4 Fork 0

赵泽伟 / reinforcement-learning

Create your Gitee Account
Explore and code with more than 8 million developers,Free private repositories !:)
Sign up
This repository doesn't specify license. Please pay attention to the specific project description and its upstream code dependency when using it.
Clone or Download
contribute
Sync branch
Cancel
Notice: Creating folder will generate an empty file .keep, because not support in Git
Loading...
README.md

环境

  • tensorflow 1.8
  • numpy
  • gym
  • pybox2d

Deep Q Network

  1. 使用说明:

执行python lunar_lander.py [-d] [-D] [-r] [-l] [-t]命令运行程序。

-d: 使用Dueling DQN

-D: 使用Double DQN

-r: 展示游戏画面

-l: 输出tensorboard log文件

-t: 训练模式

如果你想使用Dueling DQN 并且使用 Double DQN对LunarLander环境进行训练,执行

python lunar_lander.py -d -D -t

如果你想读取保存好的模型,展示游戏画面,执行

python lunar_lander.py -d -D -r

注意:如果训练的时候使用了Dueling DQN -d,则读取的时候记得也要带上 -d

  1. 结果:

CartPole

LunarLander

About

强化学习实现gym环境,持续更新,已有dqn实现cartpole、lunarlander expand collapse
Python
Cancel

Releases

No release

Contributors

All

Activities

Load More
can not load any more
Python
1
https://gitee.com/kdldbq/reinforcement-learning.git
git@gitee.com:kdldbq/reinforcement-learning.git
kdldbq
reinforcement-learning
reinforcement-learning
master

Search