I'm currently following University of California's Computer Science 285 classes, which can be found at this address: http://rail.eecs.berkeley.edu/deeprlcourse/
The lectures can be found at: https://www.youtube.com/watch?v=JHrlF10v2Og&list=PL_iWQOsE6TfURIIhCrlt-wj9ByIVpbfGc&index=1
Another set of lectures that I'll draw inspiration from is: https://www.youtube.com/watch?v=qaMdN6LS9rA&list=PLAdk-EyP1ND8MqJEJnSvaoUShrAWYe51U
I've also read (though without paying too much attention, I'll admit) Sutton and Barto's "Reinforcement Learning: an Introduction", considered by many the holy book of this discipline, along with Zai & Brown's "Deep RL in Action" and Maxim Lapan's "Deep RL Hands-On". Those have all been very useful, I strongly recommend them to anyone interested in picking up Reinforcement Learning on their own.
I've also completed University of Alberta's Reinforcement Learning Certification on Coursera, which helped me dip my toes into the coding part (although I didn't give it the time it deserved); also DeepLizard's series on YouTube was my very first exposition to RL almost a year ago now, and I am very grateful for their excellent explanations.
As you can see I've taken RL coursees before, but this is going to be the first time I'll be truly going in, listening to the lectures multiple times, taking notes and trying to understand every concept that's being taught.
I'll also try to go from theoretical knowledge to working code, and that's perhaps the challenge that scares me the most, as I tend to stick to notions instead of trying to make things work, a very bad habit of mine. I have to try for myself, I have to fail, it's the only way to learn.
So, this is the beginning of my blog, I hope I'll be able to share some knowledge with you and make your life a bit easier :)
See you soon!
-Fuma
Comments