CS294-112 深度强化学习 秋季学期（伯克利）NO.9 Learning policies by imitating optimal controllers

 

 

 

扫描二维码关注公众号，回复： 1057647 查看本文章

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

make compromise between learnt policy and minimal cost！

                    

                     

 

 

 

 

π hat is using states

π theta is using observations