Re: [sl4] JAGI submission

From: Peter de Blanc (peter@spaceandgames.com)
Date: Wed Nov 26 2008 - 12:29:30 MST


Matt Mahoney wrote:
> The rate of information gain for RSI is O(log t). The information gain for evolution is O(t), or 1 bit per population doubling and selection.
>
> -- Matt Mahoney, matmahoney@yahoo.com

Matt, RSI gains O(log t) bits compared to a Kolmogorov prior, while
evolution gains O(t) bits compared to a uniform prior. You can't compare
these two quantities.



This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:01:03 MDT