5分钟搞清楚强化学习强在哪？

篇幅有限，蒙特卡洛没讲
参考资料:
   • Reinforcement Learning (RL) - Andrew ...  
   • I Talked with Rich Sutton  
   • The Tea Time Talks: Rich Sutton, Are ...  
   • Andrew G. Barto - Closing Remarks & M...  
   • TURING AWARD WINNER Richard S. Sutton...  
   • Rich Sutton (DeepMind Alberta, Univer...  

#Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems
https://github.com/david78k/pendulum/...

#Learning to predict by the methods of temporal differences
https://link.springer.com/article/10....
#The Bitter Lesson
http://www.incompleteideas.net/IncIde...
#Q learning
https://link.springer.com/article/10....
#DQN
https://arxiv.org/abs/1312.5602