Check out Janggi (Korean Chess), our featured variant for November, 2024.

Enter Your Reply

The Comment You're Replying To
Joe Joyce wrote on Thu, Dec 14, 2017 09:12 AM UTC:

Aurelian, I've read the first part of the paper V. Reinhart linked a bit after our comments. My math was always bad, but I think this is a relevant paragraph in the paper:

Instead of an alpha-beta search with domain-specific enhancements, AlphaZero uses a general-purpose Monte-Carlo tree search (MCTS) algorithm. Each search consists of a series of simulated games of self-play that traverse a tree from root s root to leaf. Each simulation proceeds by selecting in each state s a move a with low visit count, high move probability and high value (averaged over the leaf states of simulations that selected a from s) according to the current neural network fθ. The search returns a vector π representing a probability distribution over moves, either proportionally or greedily with respect to the visit counts at the root state.

I believe that it would take a truly remarkable neural net to significantly outperform all humans either individually or as teams playing as a general staff, because the sheaves of probability explode from each potential group of moving pieces interacting with each different board or even different entry squares or entry times presented.

Let me offer you a link to a website under construction that steps through the first "day" of a purely combinatorial abstract strategy combat simulation, which includes 24 sequential "daylight" turns alternating between blue and red, and a lesser number of "night" turns to finish all combat, separate the 2 sides, "rally" troops - return 1/3rd of each side's losses to the owning player to drop by friendly leaders. Marked reinforcements come in between turns 8 & 9 (4 turns for each side) on their assigned entry areas, are unmarked and move normally from the start of the next daylight turn. The sequence above is repeated again, with on-board sides each being reinforced twice, once on daylight turns 29/30 and again on 39/40. After a second night, a 3rd day with no reinforcements is played. If none of the 3 criteria for victory has been achieved by either player, both lose. Otherwise, a victor or a draw is determined.

http://anotherlevel.games/?page_id=193 (please wait for it to load - thanks! Said it's under construction!)

Note terrain blocks movement and is completely variable. There are a handful of elements I put in each version of the scenario, a "city" of around 10 squares in the center of the board, a "mountain in the northwest quadrant of the board, a "forest" in the south, a "ridge" running from NE to SE of the city's east edge, a light scattering of terrain to break up and clog up empty areas on the board, and a dozenish entry areas. Nothing need be fixed from game to game. How does even a great neural net do better than any human or team every single time? There are far too many possibilities for each game state, and truly gigantic numbers of game states, in my semi-skilled opinion.


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.
Avoid Inflammatory Comments
If you are feeling anger, keep it to yourself until you calm down. Avoid insulting, blaming, or attacking someone you are angry with. Focus criticisms on ideas rather than people, and understand that criticisms of your ideas are not personal attacks and do not justify an inflammatory response.
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.