2018年5月27日
CS294-112 深度强化学习 秋季学期（伯克利）NO.9 Learning policies by imitating optimal controllers
摘要： make compromise between learnt policy and minimal cost！ π hat is using states π theta is using observations 阅读全文
posted @ 2018-05-27 23:01 ecoflex 阅读(198) 评论(0) 推荐(0)
CS294-112 深度强化学习 秋季学期（伯克利）NO.8 Learning dynamical system from data
摘要： MPC means replan every step Every N step, rebuild the dynamic model 阅读全文
posted @ 2018-05-27 18:15 ecoflex 阅读(247) 评论(0) 推荐(0)