gym强化学习入门demo——随机选取动作 其实有了这些动作和反馈值以后就可以用来训练DNN网络了...
# -*- coding: utf-8 -*-import gymimport timeenv = gym.make('CartPole-v0')observation = env.reset()print(observation)print("env actionspace：")print(env.action_space)print(...
