homework of CS294-112

• hw1 Behavioral-Cloning and DAgger
• hw2 Policy-Gradient
• hw3 Actor-Critic, Q-learning
• hw4 Model-Based RL
• hw5

源代码：https://github.com/berkeleydeeprlcourse/homework

参考：

https://github.com/Observerspy/CS294

https://github.com/xuwd11/cs294-112_hws

https://zhuanlan.zhihu.com/c_150977189

https://zhuanlan.zhihu.com/codekitty