Allure Love的博客

1.gym环境video.mp4记录 ubuntu需安装sudo apt-get install ffmpeg import gym from gym import wrappers env = gym.make("CartPole-v0") env = wrappers.Monitor(env, "./") for i_episode in range(1): observation = env.reset() for t in range(100): env.re

1 https://www.jianshu.com/p/43318a3dc715?isappinstalled=0

1.对于强化学习中策略梯度为什么取log的问题 https://blog.youkuaiyun.com/qq_39004117/article/details/91465973

1.Actor-Critic算法详解 https://blog.youkuaiyun.com/qq_30615903/article/details/80774384 2.DDPG https://blog.youkuaiyun.com/qq_30615903/article/details/80776715