My goal is to understand AlphaZero paper published by deepmind. I'm beginning my journey trying to get the basic intuition of reinforcement learning from the book by Barto and Sutton.

As per my background, I'm familiar with MDPs, value iteration and policy iteration.

I wanted to ask until what chapter of Barto and Sutton's book is one required to read in order to fully comprehend AlphaZero's paper. Monte-Carlo Tree Search is discussed in Chapter-8 of the book. Will it be enough till that? Or would I be needing more resources apart from this book?

  • 1
    $\begingroup$ Start reading the paper and look up the things that you don't understand or ask a question about it. $\endgroup$
    – Brale
    Jun 18, 2019 at 21:12
  • $\begingroup$ After completing the relevant chapter of the book, I would suggest you take a look at the cited references in the paper (especially those parts that you feel you need more materials). $\endgroup$ Jun 20, 2019 at 1:24
  • $\begingroup$ @Brale yes, this worked for me with GPT-2... however, the tree of unknowns is quite deep! $\endgroup$
    – user253751
    Oct 12, 2021 at 8:50

1 Answer 1


The more you read, the more deeply you can understand any paper, but given your stated background, reading the Monte-Carlo Tree Search chapter of Barto & Sutton, plus Gerald Tesauro's TD-Gammon paper (which is pretty accessible, and which is the basis for the other technique used in AlphaZero) should be enough to get a pretty good idea of what they did.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .