Reinforcement Learning – Bandit Problems

Re:Reinforcement Learning – Bandit Problems by subatomic on Monday May 07, 2018 @01:28AM (#17010580)

I was heavily into reinforcement learning around the turn of the century, and at the time, "Reinforcement Learning - An introduction" (Barto and Sutton) https://mitpress.mit.edu/books/reinforcement-learning was an absolute goldmine for me getting started. I think parts of it are online somewhere including all their pseudocode and solutions.

https://mitpress.mit.edu/books/reinforcement-learning

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by svalorzen on Monday May 07, 2018 @03:13AM (#17010901)

The complete first edition can be found here: http://incompleteideas.net/book/ebook/the-book.html

If you're interested in some well documented C++ implementations of the algorithms shown in the book, feel free to check out https://github.com/Svalorzen/AI-Toolbox. I started the project because when I was first reading the book I had no reference implementation to compare the book to, and personally I learn better with practical examples, so maybe it can help you too.

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by levesque on Monday May 07, 2018 @09:56AM (#17012709)

If you are going to start in RL, you should really consider reading the second edition even though it is not released yet. I am guessing that Sutton is getting closer to the finishing line as there have been numerous revisions already. The second edition has better notation and benefits from the field having matured a lot since the first book was written. http://incompleteideas.net/book/the-book-2nd.html

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by johnmoberg on Monday May 07, 2018 @02:20AM (#17010725)

It's a fantastic book! The authors have been working on a second edition for a few years, and I think it's finally finished. A draft is generously available here: http://incompleteideas.net/book/the-book-2nd.html

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by lpage on Monday May 07, 2018 @11:32AM (#17013514)

As a self contained, foundational course, Georgia Tech's OMSCS offering [1] is solid. Charles Isbell and Michael Littman are great at building intuition into equations.

[1] https://www.udacity.com/course/reinforcement-learning--ud600

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by joshuamorton on Monday May 07, 2018 @11:48AM (#17013681)

Isbell's course in person was great. And if the exams for the online version are anything like the in person ones, it really does test your understanding of foundational concepts.

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by richfnelson on Tuesday May 08, 2018 @06:18PM (#17025789)

Yup, just took the online RL class and the average grade for the final exam was 45 out of 100, high score of 76. The format was true/false with a short explanation for your answer. I never thought I'd be proud about getting a 53 on a true/false exam, but it was an extremely challenging and rewarding class.

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by pure-awesome on Monday May 07, 2018 @03:10AM (#17010889)

I was wondering how you were over 120 years old there, for a moment, then I realized turn of the century doesn't mean that century any more.

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by alexcnwy on Monday May 07, 2018 @08:30AM (#17012188)

Bartow & Sutton is excellent.

You can definitely find it online but be sure to find the right version - the latest version has great illustrations and is a lot clearer.

Also, check out the RL jupyter notebook here by my friend Ryan Sweke who does work on RL for quantum computing: https://github.com/R-Sweke/CrashCourseInNeuralNetworksWithKe...

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by oneraynyday on Monday May 07, 2018 @08:16AM (#17012127)

Great suggestion! The blog was based on a large portion of the book. A friend of mine asked for a version of the first chapter that was digestible for an audience that is in high-school to undergrad college level. I wrote this blog with that in consideration, while adding my own observations as well. I am planning to write up some python solutions for the MDP chapter as well. Thanks for reading :)

[ Parent | on HN ]

Re:Reinforcement Learning – Bandit Problems by markatkinson on Monday May 07, 2018 @05:20AM (#17011339)

Thanks for this, I have read a couple books on deep learning but struggled to find anything on Reinforcement Learning. Maybe an Ask HN is in order.

[ Parent | on HN ]