<a href="https://www.alexirpan.com/2018/02/14/rl-hard.html" rel="nofollow">https://www.alexirpan.com/2018/02/14/rl-hard.html</a> Reinforcment learning for the average person is a big waste of time. Probably for anyone atm
I think "learn" is a bit misleading here but I do have to say it's a nice and intuitive overview of RL.
RL is quite hard and math heavy, I don't know if one can take a short cut in learning RL without solid graduate level math foundation.
A small tangential criticism, but using "deep" every other sentence and especially expressions like "classical deep learning" made me take this article less seriously.<p>This is not unique to this author, sadly. I'm tired of seeing the d word thrown in research papers just for the sake of adding more buzzwords per buzzword.<p>Once you've made clear you are using neural networks with a lot of layers you can start using some variation in the discourse. Maybe just call them neural networks...
There were so many technical terms, I'm surprised you could get through even an overview, and then practicals, in just 4 hours.<p>Do you know of any resources which list most of the common alternatives? e.g. what are the alternatives to a3c for parallelizing; or the alternatives to a2c for getting policy and value estimates?