This repo includes lecture slides, notebooks and other material for the RL week at AMMI, the African Masters of Machine Intelligence
Lec 1: From basic concepts to deep Q-networks
Extra:
- Supplementary: Policy/Value Iteration in Matrix form
- RL book Chapter 4, Dynamic Programming
- Dynamic Programming lecture video
- To communicate directly with the tutors, chat to us here: https://www.tinyurl.com/chat-to-us
- To put a question forward to the tutors and your peers, open an 'issue' with the label 'question' example-clickMe
-
('^__^') Sutton and Barto (4.7/5)
-
Solutions
-
Chap 1 - 9 ( /5)
-
Chap 1,2, 13 (with summaries) ( /5)
-
Chap 1-3 (with code) ( /5)
-
Chap 1-3 (with code) ( /5)
-
-
Code (of content)
- Chap 1 - 13, Python ( /5)
- Chap 1 - 13, Lisp ( /5)
-
-
(^_^) Wild ML (Denny Britz) - Meta-course (recommended reading, exercises from other courses, implementations) with implementations, Python ( /5)
-
(^_^) Dave Silver ( /5)
-
(-)Coursera - Practical RL ( /5)
-
(^_^) Coursera - University of Alberta - 4 part specialization (3/5)
-
(",) Udacity
Really great playlist of videos 5min each about 200 of them - well labelled, so that if you want to find a specific thing to learn / revise it is easy to find - very comprehensive - give it a look I reckon
-
(^_^) Deeplizard - RL playlist - 18 Vids ( /5)
-
(^_^) YouTube playlist ( /5)
- (",) Free code camp - ( 4/5) - good overview
- (",) Medium, RL algorithm review (3/5)
- (",) Medium, RL overview (3/5)
- (",) Summary of terminology (3.5/5)
- (",) overviews of contemporary RL
