Abstract
It was a pleasure to read the clear article on dynamic komi, written by Petr Baudis (2011) in the September issue of the ICGA Journal. Especially his first two sentences were a concise description of the basic problem: “Monte-Carlo Tree Search tends to produce unstable and unreasonable results (...) when used in positions with an extreme advantage or disadvantage. This is due to a poor move selection because of the low signal-to-noise ratio.”
In this note I want to provide additional material on different aspects of dynamic komi: (1) on the history of the name, (2) on manually operated dynamic komi, (3) on hard workers in the sewerage, and (4) on a newly created handicap prize.
Get full access to this article
View all access options for this article.