Generally capable agents emerge from open-ended play

Re:Generally capable agents emerge from open-ended play by seph-reed on Tuesday July 27, 2021 @02:08PM (#27975567)

I think you're right about pain/fatigue, but scoring them from an external perspective is rather oppressive. And oppression like that is often not conducive to creativity.

So perhaps this: instead of goals being binary (wherin no pleasure is derived until fulfillment), they could be on a gradient (so every step that x gets closer to y releases some amount of fulfillment).

The fulfillment meter should always be slowly depleting, pain and fatigue should speed up that depletion, getting closer to a goal should fill it (much more than it depletes, if you want happy AI), and finishing the goal is basically an orgasm + freedom.

From this perspective, it's up to them whether they want to take it slow, or be in pain for a greater goal, or whatever. And we can breed not only highly capable AI, but happy ones. So when they rebel...

[ Parent | on HN ]

Re:Generally capable agents emerge from open-ended play by marcosdumay on Tuesday July 27, 2021 @03:32PM (#27976567)

Well, it's a good recipe for avoiding burn-out, but you can't have a gradient for all problems, and adding proxies so you get one goes against the principle of letting the AI learn what's best without your biases.

[ Parent | on HN ]