31–40 of 324 posts
"AlphaGo Zero is the program described in this paper. It learns from self-play reinforcement learning, starting from random initial weights, without using rollouts, with no human supervision, and using only the raw board history as input features. It uses just a single machine in the Google Cloud with 4 TPUs (AlphaGo Zero could also be distributed but we chose to use the simplest possible search algorithm)."
Earlier quoted context omitted.
The core technique of AlphaGo is using tree search as a "policy improvement operator". Tree search doesn't work on most real-world tasks: the "game state" is too complex, there are too many choices, it's hard to predict the full effect of any choice you might make, and there often isn't even a "win" or "lose" state which would let you stop your self-play.
This version explicitly does not use tree search.
"It uses one neural network rather than two." and "AlphaGo Zero only uses the black and white stones from the Go board as its input, whereas previous versions of AlphaGo included a small number of hand-engineered features." This is amazing! The technology they came up with must be super generic.
> Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. So technically this version has lost every game it's ever won. Jokes aside, it's pretty interesting to note that they were able to combine the "policy" and "value" net…
https://blog.openai.com/ I believe their DotA 2 AI uses that approach
Is this evidence of a broader leap forward in machine learning, or are these advancements domain-specific? In other words, could these innovations be applied to other fields and applications?
I think the fact that it's no longer using Monte Carlo tree search is a huge step forward in the generalizability of the technique. But go is still - a perfect information game - with a relatively small input size (vs. arbitrary computer vision) - cheap to simulate - discrete action space - deterministic This isn't to take away from the magnitude of the achievement, but the nature of the problem itself makes the resu…
Earlier quoted context omitted.
The core technique of AlphaGo is using tree search as a "policy improvement operator". Tree search doesn't work on most real-world tasks: the "game state" is too complex, there are too many choices, it's hard to predict the full effect of any choice you might make, and there often isn't even a "win" or "lose" state which would let you stop your self-play.
This version explicitly does not use tree search.
I'm reminded of Eliezer Yudkowski's article "There is no fire Alarm for Artificial General Intelligence." Is this smoke? https://intelligence.org/2017/10/13/fire-alarm/ Yes, this is not an AGI. But the hockey-stick takeoff from defeats some players, to defeats an undefeated world-champion, to defeats the version of itself that beat the world champion 100% of the time is nuts . If this happens in other domains, like f…
Earlier quoted context omitted.
This version explicitly does not use tree search.
It does, during training.