[ExI] Whistling past the graveyard

[Anders Sandberg]

On 2016-04-07 14:57, William Flynn Wallace wrote:
> Before I reply to this thread, please John or someone, answer this;
>
> Is an AI always programmed to take the most likely route to success - 
> the highest probability, once it has considered alternative routes? 
> People might have other motivations.   (to me, this gets us directly 
> into the free will problem, which y'all might not want to repeat)

In the reinforcement learning systems I know the best the actions 
undertaken are likely to be best, but there is a chance for 
"exploratory" other actions.

As The Book puts it:
https://webdocs.cs.ualberta.ca/~sutton/book/2/node3.html
https://webdocs.cs.ualberta.ca/~sutton/book/2/node4.html

Things get more complex when the action has parts.

-- 
Anders Sandberg
Future of Humanity Institute
Oxford Martin School
Oxford University

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20160407/ab5543c4/attachment.html>