0
$\begingroup$

I cannot find reliable sources but someone says it is 40 moves and someone else says it is 50+ moves. I read their papers and they use value function (NN) and policy function to trim the tree, so more layers can be searched while spending less time searching less different positions.

My question is, is the search depth a fixed preset parameter? If so, approximately how much is it back to 2016 (AlphaGo) and 2018 (AlphaGo Zero)?

$\endgroup$
1
$\begingroup$

For easier visualization, I recommend this video: https://twitter.com/i/status/1257053365424578565

The more detailed article about GO algorithms: https://deepmind.com/blog/article/alphago-zero-starting-scratch.

With its breadth of $250$ possible moves each turn (go is played on a $19$ by $19$ board, compared to the much smaller $8$ by $8$ chess field) and a typical game depth of $150$ moves, there are about $250^{150}$, or $10^{360}$.

After $2$ moves in go, it's $130000$ possible combinations.

Decision tree pruning

enter image description here

$\endgroup$
2
  • $\begingroup$ Do you know the approximate depth or the average depth? $\endgroup$
    – High GPA
    Sep 21 '20 at 19:45
  • 1
    $\begingroup$ if it'll be Monte Carlo Tree Search - then hypothesizes 3-5 deepth or 5-15 (with prunning) (depend on CPU, GPU) $\endgroup$
    – Piotr Żak
    Sep 22 '20 at 12:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.