Re: Random Determination in AI

From: David Kinny (dnk@OMIT.cs.mu.oz.au)
Date: Tue Feb 06 2001 - 06:36:14 MET

  • Next message: Stephan Lehmke: "Nice instructive application example for fuzzy control"

    mattj33@yahoo.com (Matt Wells) writes:

    >Hi everyone,

    >It's nice to find a place where people discuss AI and ALife. I'd just
    >like to invite everyone to visit my web site where I disucss my AI
    >theory called Random Internal Input Interpreation. The basic idea is
    >that rather than having an agent attempt to build a knowledge base of
    >logical relations in a hopelessly complex world, it instead randomly
    >selects actions to try out, evaluates their effectiveness, then biases
    >favourable actions for the next random selection. [...]

    Hi Matt,
     
    The idea of agents randomly selecting actions and evaluating their
    effectiveness is rather well known, and you are wrong to suggest (as
    you do on your website) that existing AI algorithms don't employ such
    techniques. Take a look at the topic of "reinforcement learning" in
    general and "Q learning" in particular.
     
    David

    ############################################################################
    This message was posted through the fuzzy mailing list.
    (1) To subscribe to this mailing list, send a message body of
    "SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at
    (2) To unsubscribe from this mailing list, send a message body of
    "UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"
    to listproc@dbai.tuwien.ac.at
    (3) To reach the human who maintains the list, send mail to
    fuzzy-owner@dbai.tuwien.ac.at
    (4) WWW access and other information on Fuzzy Sets and Logic see
    http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info
    (5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html



    This archive was generated by hypermail 2b30 : Tue Feb 06 2001 - 06:46:27 MET