篇幅有限，蒙特卡洛没讲
参考资料:
https://www.youtube.com/watch?v=D-VULoe0IPI
https://www.youtube.com/watch?v=4feeUJnrrYg
https://www.youtube.com/watch?v=g80wiWvOtvI
https://www.youtube.com/watch?v=e6rGgZVgasE
https://www.youtube.com/watch?v=9_PepvnqIfU
https://www.youtube.com/watch?v=n40MmsHmYrwhttps://www.youtube.com/watch?v=NvfK1TkXmOQ
#Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems
https://github.com/david78k/pendulum/blob/master/c/anderson/Neuronlike%20Adaptive%20Elements%20That%20Can%20Solve%20Difficult%20Learning%20Control%20Problems%20Barto1983.pdf
#Learning to predict by the methods of temporal differences
https://link.springer.com/article/10.1007/BF00115009
#The Bitter Lesson
http://www.incompleteideas.net/IncIdeas/BitterLesson.html
#Q learning
https://link.springer.com/article/10.1007/BF00992698
#DQN
https://arxiv.org/abs/1312.5602
