2018年4月30日
Deep RL Bootcamp Lecture 4A: Policy Gradients
摘要： in policy gradient, "a" is replaced by "u" usually. use this new form to estimate how good the update is. If all three path show positive reward, shou 阅读全文
posted @ 2018-04-30 20:37 ecoflex 阅读(230) 评论(0) 推荐(0) 编辑
Deep RL Bootcamp Lecture 3: Deep Q-Networks
摘要： https://www.youtube.com/watch?v=fevMOp5TDQs http://www.denizyuret.com/2015/03/alec-radfords-animations-for.html artari is not a MDP, but MDP method wo 阅读全文
posted @ 2018-04-30 16:41 ecoflex 阅读(185) 评论(0) 推荐(0) 编辑
Deep RL Bootcamp Lecture 2: Sampling-based Approximations and Function Fitting
摘要： ... 阅读全文
posted @ 2018-04-30 16:03 ecoflex 阅读(124) 评论(0) 推荐(0) 编辑
Deep RL Bootcamp Lecture 1: Motivation + Overview + Exact Solution Methods
摘要： https://www.youtube.com/watch?v=qaMdN6LS9rA https://drive.google.com/file/d/0BxXI_RttTZAhVXBlMUVkQ1BVVDQ/view match: a4 b1 c2 d3 a The middle one is c 阅读全文
posted @ 2018-04-30 14:52 ecoflex 阅读(204) 评论(0) 推荐(0) 编辑