|
From: | Timothy Y. Chow |
Subject: | Re: current development |
Date: | Wed, 4 Dec 2019 14:50:59 -0500 (EST) |
User-agent: | Alpine 2.21 (LRH 202 2017-01-01) |
On Thu, 5 Dec 2019, Joseph Heled wrote:
To do a "AlphaGammon" would require, at a minimum, one or more googlers who have worked on AlphaGo or AlphaChess and are willing to contribute time and resources.
The situation is rosier than that, in my opinion. In chess, for example, Leela Chess Zero and Fat Fritz are approaching AlphaZero in chess strength, if they have not already attained it. This demonstrates that the ideas behind AlphaZero have percolated into the wider machine learning community and are not locked behind Google's proprietary closed doors. If we're not already at the point where AlphaGammon could be someone's graduate thesis, then we're very close to it.
Tim
[Prev in Thread] | Current Thread | [Next in Thread] |