In the development of self driving cars the solution to this was to take real world data and then to distort this input in various plausible ways effectively multiplying a single experience into many experiences.
On Wed, Oct 21, 2015 at 1:13 PM, Ben Goertzel <[email protected]> wrote: > >> I have a last consideration that I think is very important about the hard >> or soft take off. >> >> Once an AGI with the minimum characteristics above mentioned will be >> created, it will have to be trained in dealing with the real world and it >> will take a long time because the feedbacks form our world are very slow >> and not repetitive. The Agent will have to gain experience as we do and it >> will not matter how fast the Agent will process the information, it will >> still have to wait for feedbacks. It may take years, it may be like rising >> a child, nothing like an overnight full immersion. >> >> How close are we to this? >> >> > > That doesn't make sense to me, because an AGI agent will not be restricted > to a single human-like robot body to learn with -- it will be able to learn > in parallel from the world, using a host of different sensors and > actuators... The degree to which is can exploit this potential for > massively parallel learning will depend on the particular AGI architecture, > right? > > -- Ben > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/26973278-698fd9ee> | > Modify > <https://www.listbox.com/member/?&;> > Your Subscription <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
