Re: Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
Adrian Petrescu <[email protected]>
| Newsgroups | gmane.games.devel.go |
|---|---|
| Message-ID | <[email protected]> |
On 12/19/2017 12:25 PM, Marc Landgraf wrote:
> There is not much to achieve there though.
>
> It is expected that an AI will be able to outplay a Human opponent simply
> on micro tricks. Perfect single unit micromanagment across the entire map
> can easily gain a large enough edge, that the strategic decision making
> with imperfect information doesn't have to reach too high levels.
> So most likely any win the AI will achieve will be discredited by the Human
> players due to this.
They've gone to great lengths to mitigate this exact criticism. The
output actions are limited to human-like APM levels, and they aren't
omnipresent - the AI has to pan the screen, click the cursor, etc., the
same as a human would, at human-like speeds. You should read the paper -
they want to make sure the advantage comes purely from the quality of
the decision-making.
--
Adrian
_______________________________________________
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go