--- Mike Tintner <[EMAIL PROTECTED]> wrote: > Screw the algorithms. Why not try some nondeterministic programming, and > let the agent work things out through trial and error? The way we actually > are programmed?
Isn't learning from trial and error a type of algorithm? -- Matt Mahoney, [EMAIL PROTECTED] ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=4007604&user_secret=8eb45b07