https://github.com/syyxtl/RL-learn
我会不断学习RL,然后跟着书籍编写RL学习代码:
目前完成:
K-bandits:了解ep-greedy
dp,dp2:dp method
random_walk:MC,TD(0)
cliff_walking_sarsa, cliff_walking_Qlearning:sarsa,Q-learning
random_walk_1000:linear-function fit method(doing)
to do others
强化学习学习
猜你喜欢
转载自blog.csdn.net/qq_36336522/article/details/107929332
今日推荐
周排行