Why is successes - failures a poor measure of usefulness? Particularly for a plan or solution? Kindly advise. ~PM
> Date: Sat, 27 Sep 2014 23:01:30 -0400 > Subject: Re: [agi] How many tries? > From: [email protected] > To: [email protected] > > On Fri, Sep 26, 2014 at 9:19 PM, Piaget Modeler via AGI <[email protected]> > wrote: > > reliability = successes / attempts. > > > > utility = successes - (attempts - successes) > > No. By utility I mean value, for example, dollars. Utility is a > function that defines the goal in a reinforcement learner. (Not that I > recommend this as the primary means of learning). > > -- > -- Matt Mahoney, [email protected] > > > ------------------------------------------- > AGI > Archives: https://www.listbox.com/member/archive/303/=now > RSS Feed: https://www.listbox.com/member/archive/rss/303/19999924-4a978ccc > Modify Your Subscription: https://www.listbox.com/member/?&; > Powered by Listbox: http://www.listbox.com ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
