They mention a documentary on Netflix about AlphaGo. Any recommendations for or against?
Really good. As other people mentioned, it's not technical, but it's super interesting to see the emotional impacts those games had on Lee Sedol.
How AlphaZero Mastered Its Games
21–30 of 80 posts
Re: How AlphaZero Mastered Its Games
#22Earlier quoted context omitted.
I strongly suspect alphazero is easily beatable, once you have your hands on it. This is just from experience that most neural network style systems are weak against adversarial opponents who understand their internals. Of course I can't be sure, because Google refuses to give out anyone access to alphazero, or a network trained with it. Personally, that gives me more confidence they know there are significant exploi…
Adversarial? If the model exclusively trains against itself, you can’t really insert anything there. Do you mean, play confusing moves at the beginning of the game?
I mean, if we had the network, it would be easy to beat, the same way you can confuse image recognition systems with very minor changes.
Re: How AlphaZero Mastered Its Games
#23They mention a documentary on Netflix about AlphaGo. Any recommendations for or against?
Watched and really enjoyed.
Re: How AlphaZero Mastered Its Games
#24Is there a way to play against an AlphaGo or equivalent but with adaptive difficulty? I know next to nothing about go and think it would be interesting to learn it just by playing vs. a neural network. Maybe over time the strategies it uses would be "transferred" over to me!
Re: How AlphaZero Mastered Its Games
#25Earlier quoted context omitted.
Adversarial? If the model exclusively trains against itself, you can’t really insert anything there. Do you mean, play confusing moves at the beginning of the game?
I mean, if we had the network, it would be easy to beat, the same way you can confuse image recognition systems with very minor changes.
That doesn't follow. For you to confuse it, you need to change the inputs. For images, this is fine, we can smoothly change lots of little things. For chess games or go you don't have that freedom.
You can download the weights for LCZero right now though and try out your theory. https://github.com/LeelaChessZero/lc0/wiki/Getting-Started
Re: How AlphaZero Mastered Its Games
#26The match between Stockfish and AlphaZero was played with certain unjustified parameters (time control, ponder off, different hardware, no opening book or endgame tablebase for Stockfish etc.). By "unjustified," I mean that the authors of the paper did not justify their choice of parameters in the paper as being designed to implement a fair match.
At a glance, the parameters of the match seem unfair to me -- and tilted heavily towards AlphaZero. If the code, were open source, this would not matter; anyone could run a rematch. As it is, I haven't seen any convincing evidence that AlphaZero is stronger than Stockfish when Stockfish is allowed to use its full breadth of knowledge and run on equal hardware.
Re: How AlphaZero Mastered Its Games
#27The match between Stockfish and AlphaZero was played with certain unjustified parameters (time control, ponder off, different hardware, no opening book or endgame tablebase for Stockfish etc.). By "unjustified," I mean that the authors of the paper did not justify their choice of parameters in the paper as being designed to implement a fair match. At a glance, the parameters of the match seem unfair to me -- and tilt…
That was the first paper.
Second paper they played fair even giving stockfish a 10 to 1 advantage on same hardware as tcec uses.
Re: How AlphaZero Mastered Its Games
#28The match between Stockfish and AlphaZero was played with certain unjustified parameters (time control, ponder off, different hardware, no opening book or endgame tablebase for Stockfish etc.). By "unjustified," I mean that the authors of the paper did not justify their choice of parameters in the paper as being designed to implement a fair match. At a glance, the parameters of the match seem unfair to me -- and tilt…
There has been a rematch recently vs Stockfish, with a couple of hundred games. AlphaZero won 155-6! [0] There are fascinating videos with grandmasters commentating on some of the games. They're played in an exciting, sacrificial, swashbuckling style, nothing like any other top computer engine, and it seems that may affect the play of top (human) players for the better. e.g. see
Matthew Sadler on chess24
https://www.youtube.com/watch?v=JacRX6cKIaY&list=PLAwlxGCJB4...
Daniel King
https://www.youtube.com/watch?v=pFtY7gNRVRI&index=3&list=PLh...
Re: How AlphaZero Mastered Its Games
#29The match between Stockfish and AlphaZero was played with certain unjustified parameters (time control, ponder off, different hardware, no opening book or endgame tablebase for Stockfish etc.). By "unjustified," I mean that the authors of the paper did not justify their choice of parameters in the paper as being designed to implement a fair match. At a glance, the parameters of the match seem unfair to me -- and tilt…
That was the first paper. Second paper they played fair even giving stockfish a 10 to 1 advantage on same hardware as tcec uses.
Paper is patient. We won't know until AlphaZero participates in a fair tournament, like Leela, which recently came in third after Stockfish.
Re: How AlphaZero Mastered Its Games
#30If you are interested in how to build a bot, Manning is having a Go bot competition:
https://deals.manning.com/go-comp/
It’s been really fun to work through the books.