I am familiar with supervised and unsupervised learning. I did the SaaS course done by Andrew Ng on Coursera.org.
I am looking for something similar for reinforcement learning.
Can you recommend something?
$\begingroup$
$\endgroup$
Add a comment
|
5 Answers
$\begingroup$
$\endgroup$
To the good answers here, I would add
A brief overview of RL: Most essential concepts in one place.
Another brief overview, in presentation format.
Ben Recht's An outsider's tour of RL is pretty comprehensive and accessible.
The Bellman equations: central to the whole RL theory.
Policy gradients explained by Andrej Karpathy (mentioned in other answers as "pong from pixels", this is the link).
These barely scratch the surface of RL, but they should get you started.
$\begingroup$
$\endgroup$
There's a Youtube playlist (in the DeepMind channel) whose title is Introduction to reinforcement learning, which is a course (of 10 lessons) on reinforcement learning by David Silver.
A person who followed and finished the course wrote (as a Youtube comment):
Excellent course. Well paced, enough examples to provide a good intuition, and taught by someone who's leading the field in applying RL to games.
$\begingroup$
$\endgroup$
7
Before that ask yourself if you really want to learn about "reinforcement learning." Although there is much hype about reinforcement learning, the real-world applicability of reinforcement learning is almost non-existent. Most of the online courses teach you a very little about machine learning, so it is much better to get thorough with it, rather than proceeding towards reinforcement learning. Learning reinforcement learning is somewhat different from learning about unsupervised/supervised learning techniques.
Having said that, the fastest way to get a good grasp of reinforcement learning is as follow:
Watch Deep RL Bootcamp lectures.
To understand the math behind these techniques, refer to Sutton and Barto's Reinforcement Learning: An Introduction.
Read relevant papers (game-playing etc.).
P.S: Make sure that you are thorough with basics of neural networks, as most of the current papers in RL involve using DNNs in some or the other way as approximators.
answered Jul 3, 2018 at 14:03
-
$\begingroup$
real-world applicability of reinforcement learning is almost non-existentAlphaGo was trained with reinforcement learning. $\endgroup$ Commented Jul 3, 2018 at 14:30 -
$\begingroup$ Thanks, what I like about reinforcement learning is that it can improve itself just by doing the task over and over again. No supervision is needed. Only the model has to describe the problem correctly. $\endgroup$– Martin SCommented Jul 3, 2018 at 14:40
-
1$\begingroup$ @cantordust , check alexirpan.com/2018/02/14/rl-hard.html $\endgroup$ Commented Jul 3, 2018 at 15:00
-
$\begingroup$ @thecomplexitytheorist Yes, I am aware of that post, and yes, there are difficulties associated with RL (like any other ML method). However, these difficulties do not imply that its applicability is nil. Another successful example (also mentioned in the post) is the improvement of cooling efficiency of Google's data centres by 40% - hardly insignificant. $\endgroup$ Commented Jul 3, 2018 at 22:33
-
1$\begingroup$ @cantordust , you should read that post completely , there is no "reinforcement learning" learning involved in "improving cooling efficiency" , they have clearly mentioned that they made predictions based on past power consumption data. $\endgroup$ Commented Jul 4, 2018 at 7:17
$\begingroup$
$\endgroup$
I recently saw a course by Microsoft on edx. It is called 'Reinforcement Learning Explained'.
Here is the link: https://www.edx.org/course/reinforcement-learning-explained-0 This is not quite comprehensive but at least gives a good starting point.
$\begingroup$
$\endgroup$
I would say this post is a must to read:
https://rubenfiszel.github.io/posts/rl4j/2016-08-24-Reinforcement-Learning-and-DQN.html
