31–40 of 282 posts
Is this a library or something I can download and try training myself (on a small scale)? I'm not in a position to read the paper right now, so my apologies if that's covered in there. I want to ask just in case it's not, while this is still on the front page.
I wonder if being an expert at one game makes it easier to be an expert at another. If so, then maybe the examples are datasets, and convergence would be able to complete new tasks after a few examples.
Very happy to see this result. It's like a moral victory for humans, as alphago is more human like (discounting montecarlo search) than stockfish. Maybe deep learning will give us the next Euler, Newton, or Einstein.
Shogi, chess and Go are "perfect information games", meaning you can see the whole game state. It's a whole different thing to be able to solve games where you don't see everything (based on uncertainty).
Very happy to see this result. It's like a moral victory for humans, as alphago is more human like (discounting montecarlo search) than stockfish. Maybe deep learning will give us the next Euler, Newton, or Einstein.
Shogi, chess and Go are "perfect information games", meaning you can see the whole game state. It's a whole different thing to be able to solve games where you don't see everything (based on uncertainty).
Actually machines can have an even higher advantage in those cases, because they can be much better at estimating probabilities than humans. Think of card counting, for example.
Is this a library or something I can download and try training myself (on a small scale)? I'm not in a position to read the paper right now, so my apologies if that's covered in there. I want to ask just in case it's not, while this is still on the front page.
No. DM only occasionally releases software. Expert iteration is simple enough that someone can code it up on their own and there's already a few clones, so if anyone cares to train their own, it's doable, although it may take a while.
Leela zero (the main alphago zero replication project) is a crowd sourced computation effort that's going to take a fairly long time to get anywhere.
And from this paper: > "Training proceeded for 700,000 steps (mini-batches of size 4,096) starting from randomly initialised parameters, using 5,000 first-generation TPUs (15) to generate self-play games and 64 second-generation TPUs to train the neural networks."
Earlier quoted context omitted.
See the thing is though, Giraffe's evaluation actually was better than Stockfish's evaluation function, but it took much longer, and thus wasn't able to search as deep as Stockfish et al. So in a way, the real triumph of the AlphaGo series was the TPU and GPU army.
> So in a way, the real triumph of the AlphaGo series was the TPU and GPU army. Eh. It's still searching many fewer positions than Stockfish is.
A lot of the graphs in the paper seem to level out as they hit the level of the opponent. It makes me wonder to what extent AlphaGo Zero is merely optimizing to beat flaws in existing opponents' current implementations (even if "existing opponents" == all available opponents' data and algorithms today) rather than generalizable insights into the underlying game. Because wouldn't you expect that unless we are at the t…
It's not. It learns entirely through self play and never learns from playing it's opponent. Diminishing returns isn't unusual and happens in every domain. These AIs are probably playing close to the limit of what is possible, just not quite there yet.
Two things to note: 1) Alpha Zero beats AlphaGo Zero and AlphaGo Lee and starts tabla rasa 2) "Shogi is a significantly harder game, in terms of computational complexity, than chess (2, 14): it is played on a larger board, and any captured opponent piece changes sides and may subsequently be dropped anywhere on the board. The strongest shogi programs, such as Computer Shogi Association (CSA) world-champion Elmo, have…
Because captured pieces change sides, there is less of an "endgame" scenario, and as a beginner (like me) it is very easy to put too many captured pieces back into play, which makes it hard to defend everything and essentially you end up giving them back to your opponent
It doesn't seem to like the Sicilian Defense (1.e4 c5), which is the most popular opening by human players. I wonder if this will change opening theory?