• 投稿

David Silver 强化学习 (知识点分解）

1912
21
2018-12-17 11:13:46
未经作者授权，禁止转载
24
15
117
8
本专辑是David Silver 强化学习课程的个人剪辑笔记版本 想看原视频（同等清晰度）的小伙伴，可请前往https://www.bilibili.com/video/av24060851，或其他B站链接 大家可以对照问答文本，来有选择的学习不同知识点 https://zhuanlan.zhihu.com/c_180551461
学习笔记
Reinforcement
强化学习
深度碎片 发消息
As Simple As Possible
视频选集
（1/58）
1.1 admin textbook lecture notes
06:15
1.2 RL lays at the core of many sciences
03:01
1.3 what special about RL
02:54
1.4 RL examples and demos
09:37
1.5 define Reward in RL problem
03:44
1.6 reward examples
02:17
1.7 maximizing reward can be tricky
01:46
1.8 define agent and environment why reward scalar
04:20
1.9 define history and state in RL problem
03:26
1.10 what is environment state
03:42
1.11 what is agent state
01:32
1.12 what is information or markov state
05:57
1.13 example of agent state for prediction
03:21
1.14 fully observable state
01:13
1.15 partial observability
04:40
1.16 major components of RL agent
01:42
1.17 what is policy
01:09
1.18 value function and example
06:39
1.19 what are model transition reward
01:36
1.20 maze example on policy value function model
02:53
1.21 value based agent categorization
02:16
1.22 policy based actor critic agent categorization
01:18
1.23 model free and model based agents
01:46
1.24 differentiat learning and planning
02:56
1.25 atari example on planning and learning
02:01
1.26 balance exploitation and exploration
03:53
1.27 prediction and control with course outline
03:54
2.1 lecture 2 outline
00:48
2.2 MDP basics
02:42
2.3 what is a markov state
01:15
2.4 what is state transition matrix
01:55
2.5 formal definition of markov decison process
01:12
2.6 student markov chain example intro
02:01
2.7 markov chain episodes and transition matrix example
03:38
2.8 Markov reward process - define reward and goal
02:32
2.9 how reward and discount construct goal
03:24
2.10 why use discount to control short far sight interest
05:03
2.11 explain value function how state sample reward discount expectation const
04:13
2.12 how value function work in short long sight mode
01:54
2.13 understand bellman equation of MRP
04:44
2.14 explain bellman equation of MRP more
05:16
2.15 explain bellman equation in matrix operation
02:15
2.16 solve bellman equation
01:53
2.17 definition of MDP with action example
03:26
2.18 policy distribution in MDP
02:54
2.19 relation between MRP and MDP
01:53
2.20 state and action value functions
02:52
2.21 Bellman expectation equation on state and action
06:32
2.22 Example on Bellman expectation equation
02:46
2.23 solve Bellman expectation equation with matrix form
01:21
2.24 QA MRP and MDP clarification
04:01
2.25 explain optimal value function with example
07:48
2.26 what is optimal policy
04:14
2.27 how to find optimal policy
02:02
2.28 explain Bellman optimality equation
06:22
2.29 Bellman optimality equation example and solution
03:57
2.30 QA to intuition of Bellman optimality equation
08:42
2.31 extention to MDP
01:49

献给所有认为数学和深度学习很重要，但认为自己“不擅长数学”的人！
深度碎片
2.3万 20

Santa Fe Institute 复杂系统公开课Complexity: An introduction
深度碎片
2.1万 34

Mathematics for Machine Learning (Coursera, Imperial college of London 完整版)
深度碎片
4.4万 103

人人必备的数学思维Mathematical thinking by Stanford University and Coursera
深度碎片
2.9万 45

图解CNN论文：尝试用最少的数学读懂深度学习论文
深度碎片
4.6万 54

吴恩达第五课RNN笔记
深度碎片
3.2万 127

李宏毅深度学习课程（全2课2017年版）笔记汇总
深度碎片
3.0万 98

图解概率笔记：葉丙成概率公开课
深度碎片
1.3万 12

图解机器学习的数学直觉：线性代数，微积分，PCA（全完结）
深度碎片
11.5万 292

哈佛通识概率普及课（特别推荐）Fat Chance: Probability from the Ground Up by Harvard and Edx
深度碎片
1.2万 28

addition_steps
深度碎片
147 0

mismanagement_genius_hypothesis
深度碎片
266 0

fuzzySearch_bgar
深度碎片
224 0

探索一句话版的机器学习与深度学习
深度碎片
1.2万 10

006_7ec8c787
深度碎片
47 0

how bile work
深度碎片
310 0

make a blog talk
深度碎片
220 0

006_d790a54b
深度碎片
133 0

图解教材:概率机器学习（Murphy)
深度碎片
1.3万 2

概率机器学习基础：MIT概率课图解笔记
深度碎片
1.8万 8
展开
你的校园Vlog，值得被更多人看见！
客服
顶部
赛事库 课堂 2021拜年纪