I am wondering that what kind of real life problems could be modelled this way.
>> 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?
Human-level control through deep reinforcement learning
41–50 of 63 posts
Re: Human-level control through deep reinforcement learning
#42Re: Human-level control through deep reinforcement learning
#43PDF: http://arxiv.org/pdf/1312.5602v1.pdf
No, this is a new paper.
Re: Human-level control through deep reinforcement learning
#44Is there a chance this paper will be available as PDF? I' finding it difficult to read the readcube version. :-(
Re: Human-level control through deep reinforcement learning
#45Is there a chance this paper will be available as PDF? I' finding it difficult to read the readcube version. :-(
http://www.nature.com/nature/journal/v518/n7540/pdf/nature14...
Maybe you have institutional access or something, but for the rest of us, that link just redirects to the abstract.
Re: Human-level control through deep reinforcement learning
#46I think qlearning is really interesting, I posted yesterday a simple implementation/demo in Javascript of qlearning. This paper goes way beyond qlearning by deducing states based on a deep neural network from the actual game rendering, really cool. Regardless, as a first intro to qlearning I had fun putting this together https://news.ycombinator.com/item?id=9105818
Re: Human-level control through deep reinforcement learning
#47Here is the marketing side of this publication in which Google scientists (aquihired from Deepmind) have developed a way to outperform humans in Atari games: http://m.phys.org/news/2015-02-hal-bests-humans-space-invade...
Re: Human-level control through deep reinforcement learning
#48Is the paper available anywhere to read without having to pay Nature? From the comments it seems as if everyone is able to read this but me! Even in their "readcube" access method, only the first page is (barely) visible, the rest seems blurred.
Re: Human-level control through deep reinforcement learning
#49Re: Human-level control through deep reinforcement learning
#50An interesting critic by Schmidhuber about this publication:
https://plus.google.com/100849856540000067209/posts/eLQf4KC9...