Re:Human-level control through deep reinforcement learning
by eveningcoffee on Wednesday February 25, 2015 @06:44PM
(#9110536)
I am wondering that what kind of real life problems could be modelled this way.
[ Parent
| on HN ]
Re:Human-level control through deep reinforcement learning
by craftit on Thursday February 26, 2015 @04:50AM
(#9111803)
All sorts, we have a machine learning service which lets you do something similar with JSON messages.
Re:Human-level control through deep reinforcement learning
by phkahler on Wednesday February 25, 2015 @09:49PM
(#9111018)
>> I am wondering that what kind of real life problems could be modelled this way.
Driving a car? Making a taco? Working the checkout counter?
Re:Human-level control through deep reinforcement learning
by craftit on Thursday February 26, 2015 @11:44AM
(#9113439)
Keeping someone entertained in a game, the longer they play the more reward you give it. I was also thinking of hooking up a face recognition system, so it can be rewarded when the user smiles.
Re:Human-level control through deep reinforcement learning
by eveningcoffee on Thursday February 26, 2015 @02:19AM
(#9111462)
So could you define an cost function for these activities?
Re:Human-level control through deep reinforcement learning
by craftit on Thursday February 26, 2015 @11:51AM
(#9113487)
I suspect setting up motivations for the AI is going to be a big research issue before too long. If you can write a simulator for the task you want to it solve, you should be able to train it. Often writing the simulator is much easier than solving a task itself. For example, the atlas robot, then can simulate it but struggle to control it.