Idle observation: my (almost) 6-month old was able to figure out how to grasp a tiny ball cookie (1cm diameter) and put it in his mouth in ~5 attempts upon seeing the cookie for the first time. Extremely high problem complexity, extremely very low training sample size.
-
-
One attempt he brought his hand to his mouth thinking he had grabbed the cookie, though he had not. So he has a model of what was supposed to happen after attempting to grab the cookie. Then he saw the cookie was still there and tried again.
Show this thread -
Interestingly the most difficult part wasn't grabbing the cookie (despite its never-seen-before size) but dropping it in his mouth (since he's grabbing with his palm, not his fingertips. Still managed to do it in a couple of attempts.
Show this thread -
He locks on a goal and keep trying until he reaches the goal. Has a clear model of what success means, what the key steps towards success are (grabbing, bringing hand to mouth, dropping cookie), and is able to invent novel strategies for each step in a handful of attempts.
Show this thread
End of conversation
New conversation -
-
-
Curiosity driven learning with exploration <-> exploitation at play here. Not necessarily thru a reward signal. Wondering if this type of behavior is naturally emergent or interwoven in us since birth?
-
A baby's life only features extremely sparse negative/positive reinforcement signals (pain / hunger / food) and thus development is almost entirely intrinsically driven.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.