Check out Glinski's Hexagonal Chess, our featured variant for May, 2024.

Enter Your Reply

The Comment You're Replying To
H. G. Muller wrote on Tue, Dec 12, 2017 08:33 PM UTC:

I have no doubt that AlphaZero could easily do most Chess variants. My previous posting in this thread was a reaction to Greg's remarks on Stockfish. There boards larger than 8x8 would indeed be a problem. For AlphaZero, not at all.

As to the maximum capacity in terms of board size: I am sure there is one in the current system. But I am also pretty sure expading those limits would just be a matter of recompiling the software, and perhaps throwing more hardware against the problem. Note that the effort on Chess used overwhelming computing power by doing things in parallel that could just as easily have been done sequentially. Like generating the self-play games. As a result it took only 4 hours for the machine to teach itself to play Chess at the 3000+ Elo level starting from just the rules, rather than 2 years.

Everything will just get slower if you would be trying larger games. Bigger doesn't always mean more complex, though, and I can imagine that there are large games that do not need much finesse to play, and still can be learned in a small number of self-play games. (I imagine something like Checkers on a very large board.)

Game play by the trained machine would also become slower if the number of moves per typical position goes up. This will expand both the game tree necessary to see the essential tactics, as well as the neural network needed to guide the search. But of course all other methods to play the game, such as human thinking, will suffer similarly.

There is one problem: AlphaZero will be able to master any given Chess variant quickly, but after that, it still cannot tell you how it should be played. Even for simple things like piece values, you would have to reverse-engineer those from the neural net, by presenting it sets of positions with material imbalances, and looking how this affects the win probabilities that it predicts on average for those positions.


Edit Form
Conduct Guidelines
This is a Chess variants website, not a general forum.
Please limit your comments to Chess variants or the operation of this site.
Keep this website a safe space for Chess variant hobbyists of all stripes.
Because we want people to feel comfortable here no matter what their political or religious beliefs might be, we ask you to avoid discussing politics, religion, or other controversial subjects here. No matter how passionately you feel about any of these subjects, just take it someplace else.
Quick Markdown Guide

By default, new comments may be entered as Markdown, simple markup syntax designed to be readable and not look like markup. Comments stored as Markdown will be converted to HTML by Parsedown before displaying them. This follows the Github Flavored Markdown Spec with support for Markdown Extra. For a good overview of Markdown in general, check out the Markdown Guide. Here is a quick comparison of some commonly used Markdown with the rendered result:

Top level header: <H1>

Block quote

Second paragraph in block quote

First Paragraph of response. Italics, bold, and bold italics.

Second Paragraph after blank line. Here is some HTML code mixed in with the Markdown, and here is the same <U>HTML code</U> enclosed by backticks.

Secondary Header: <H2>

  • Unordered list item
  • Second unordered list item
  • New unordered list
    • Nested list item

Third Level header <H3>

  1. An ordered list item.
  2. A second ordered list item with the same number.
  3. A third ordered list item.
Here is some preformatted text.
  This line begins with some indentation.
    This begins with even more indentation.
And this line has no indentation.

Alt text for a graphic image

A definition list
A list of terms, each with one or more definitions following it.
An HTML construct using the tags <DL>, <DT> and <DD>.
A term
Its definition after a colon.
A second definition.
A third definition.
Another term following a blank line
The definition of that term.