深度理解强化学习

//清华镜像 https://mirrors.tuna.tsinghua.edu.cn/anaconda/archive/
//安装anaconda

cd downloads
bash anaconda3_4.3.0-linux-x86_64.sh
//创建虚拟环境
conda create --name gymlab python=3.5
//Open AI GYM 安装
source activate gymlab
sudo apt install git
git clone https://github.com/openai/gym.git
cd gym
pip install -e '.[all]'
pip install --upgrade setuptools
pip install numpy matplotlib
pip install opencv-python
//如果安装过程中有错误发生，一般是因为环境包没有安装成功，如
Failed building wheel for atari-py
Failed building wheel for Box2D-kengz
//解决办法
sudo apt-get install cmake
sudo apt-get install -y python-numpy python-dev cmake zlib1g-dev libjpeg-dev xvfb libav-tools xorg-dev
pip install -e '.[all]'

import gym
env = gym.make('CartPole-v0')
env.reset()
for _ in range(1000):
    env.render()
    env.step(env.action_space.sample())

import gym

env = gym.make('CartPole-v0')
for i_episode in range(20):
	observation = env.reset()
	for t in range(100):
		env.render()
		print(observation)
		action = env.action_space.sample()
		observation, reward, done, info = env.step(action);
		if done:
			print("Episode finished after {} timesteps".format(t+1))
			break

3.3 深度学习环境搭建

安装官网说明进行安装tensorflow

老师环境配置参考（Win10+CUDA9.0+CUDNN7.5+tensorflow1.9+GYM1.9 + Python3.6+jupyter-notebook）

CUDA+CUDNN(最先安装): https://www.cnblogs.com/tanwc/p/9375161.html

Tensorflow安装：https://www.cnblogs.com/tanwc/p/9375161.html

// 安装jupter notebook
python3 -m pip install --upgrade pip
python3 -m pip install jupyter