I leave you with a quote and a question.
"any algorithm performs only as well as the knowledge concerning the
cost function put into the cost algorithm". Wolpert & Macready 1995
What possible ways are there for putting knowledge into algorithms
that do not require us to program it directly?
Will Pearson
Er, well, the approach we are taking in Novamente is to interact with
the system via a 3D simulation world -- it controls one agent and the
teacher controls another...
The "reward function" of the Novamente system, in this context, is
dependent on feedback achieved via the environment, which contains the
human teacher...
-- Ben
-------
To unsubscribe, change your address, or temporarily deactivate your subscription,
please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
