I am also interested in unsupervised learning. When this first came up, I found this paper: http://arxiv.org/pdf/1312.5602v1.pdf, where the authors taught a deep convolutional network to play games from the Atari console. They used what they call "Deep Reinforcement Learning", a variant of Q-learning, and the methodology is described in detail. There's even an online demo of this technique for an easier problem here: http://cs.stanford.edu/people/karpathy/convnetjs/demo/rldemo.html
It's impressive that the same network learned to play seven games with just a win/lose signal. It's also interesting that both these teams are in different parts of Google. I assume they are aware of each other's work, but maybe Aja can confirm. On Mon, Mar 16, 2015 at 11:51 AM, hughperkins2 <hughperki...@gmail.com> wrote: > > The important thing is that the games don't have to be played perfectly: > They just need to be significantly better than your current model, so you > can tweak the model to learn from them. > > Thats an important incite. I hadnt thought of that. > > Maybe could combine with some concept of "forgetting", eg weight decay, so > the net gradually unlearns some of the original, more naive, > associations? > The important thing is that the games don't have to be > played perfectly: They just need to be significantly better than your > current model, so you can tweak the model to learn from them. > > Thats an important incite. I hadnt thought of that. > > Maybe could combine with some concept of "forgetting", eg weight decay, so > the net gradually unlearns some of the original, more naive, associations? > could combine with some concept of "forgetting", eg weight decay, so the > net gradually unlearns some of the original, more naive, associations? > > _______________________________________________ > Computer-go mailing list > Computer-go@computer-go.org > http://computer-go.org/mailman/listinfo/computer-go >
_______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
