2018年5月23日
CS294-112深度增强学习课程（加州大学伯克利分校 2017）NO.4 Learning policies by imitating optimal controllers
摘要： There are some problems: mismatch of model and reality; gradient explosion so, the dynamics can be quite messy, and backpropogating can be quite probl 阅读全文
posted @ 2018-05-23 19:14 ecoflex 阅读(334) 评论(0) 推荐(0) 编辑