"Instead of a handcrafted evaluation function and move ordering heuristics, AlphaZero utilises a deep neural network (p,v) = fθ(s) with parameters θ.
This neural network takes the board position s as an input and outputs a vector of move probabilities p with components pa = Pr(a|s) for each action a, and a scalar value v estimating the expected outcome z from position s"
This seems normal to me.
"Instead of an alpha-beta search with domain-specific enhancements, AlphaZero uses a general-purpose Monte-Carlo tree search (MCTS) algorithm. Each search consists of a series of simulated games of self-play that traverse a tree from root to leaf. Each simulation proceeds by selecting in each state a move with low visit count, high move probability and high value" [emphasis mine]
This is interesting. If I understand it correctly, it basically goes deeper only after reaching a high level of hash table hits.
"AlphaZero vs Stockfish: 25 win for AlphaZero, 25 draw, 0 loss (each program was given 1 minute of thinking time per move, strongest skill level using 64 threads and a hash size of 1GB)"
This is sci-fi. I do not have a 64 core machine but on my pc Stockfish do not sacrifice a Knight for 2 pawns:
1.e4 e5 2.Nf3 Nc6 3.Bb5 Nf6 4.d3 Bc5 5.Bxc6 dxc6 6.O-O Nd7 7.Nbd2 O-O 8.Qe1 f6 9.Nc4 Rf7 10.a4 Bf8 11.Kh1 Nc5 12.a5 Ne6 13.Ncxe5?
The paper is very interesting. Nevertheless selecting only wins and stripping off all game infos from the pgn might do for non-chess scientists,
but here it is quite useless and remains doubtful.
I hope there is more to come with more details for the games and the setup.
Daniel Shawul wrote:"equal hardware", "same book", "same tb" wasn't an issue for WCCC, why now ?
They are scientists so it would be nice to compare apples to apples.
So far we know that AlphaZero is able to beat SF8 without book and tbs on their hardware in a 100 game match (while the result is significant, more games would be better)
mar wrote:While this is indeed incredible, show me how it beats SF dev with good book and syzygy on equal hardware in a 1000 game match.
Alternatively winning next TCEC should do
You suppose to run Stockfish on GPU?)
mar wrote:They are scientists so it would be nice to compare apples to apples.
AlphaZero din't used neither book nor syzygy, neither did stockfish. That sounds like apples to apples.
Obviously I'd like to see AlphaZero running on a CPU (because running SF on a TPU won't happen) and still beating SF, while allowing SF to use every means to play the best chess it can, leaving zero doubt.
I wonder if they could do it, maybe not at the moment but probably soon.
Considering the hardware at their disposal, a 100 game match seems rather short.
I'm shocked what they could accomplish without alphabeta though.
mar wrote:While this is indeed incredible, show me how it beats SF dev with good book and syzygy on equal hardware in a 1000 game match.
Alternatively winning next TCEC should do
You suppose to run Stockfish on GPU?)
mar wrote:They are scientists so it would be nice to compare apples to apples.
AlphaZero din't used neither book nor syzygy, neither did stockfish. That sounds like apples to apples.
Obviously I'd like to see AlphaZero running on a CPU (because running SF on a TPU won't happen) and still beating SF, while allowing SF to use every means to play the best chess it can, leaving zero doubt.
I wonder if they could do it, maybe not at the moment but probably soon.
Considering the hardware at their disposal, a 100 game match seems rather short.
I'm shocked what they could accomplish without alphabeta though.
Well, probably they should have give same FLOPS budget to both, that seems like the most fair you can get, given the inefficiency of switching hardware for either side.
Winning against latest Stockfish with opening book and endgame tables would be definitely even more impressive.
Very cool! I am especially surprised they still relied on a MCTS approach in chess. I don't think anybody can actually reproduce these results at the moment with hardware at home but this certainly marks a significant shift in how computer chess will develop.
I am curious what kind of performance their program would be able to achieve on sub 2k off the shelf commercial hardware. Considering the power of their TPUs I imagine the penalty would be pretty huge. Regardless, commercial hardware is a question of when, and not if. Perhaps someone will improve their approach specifically for chess in some way?
I am curious if the same amount of people will work on the tinkering form of chess programming.
The AlphaZero training system costed $ 4 millions of hardware. (figures given for alpha go zero, don't have source under hand)
The paper says they use 5,000 first-generation TPUs, and 64 second-generation TPUs. Such hardware is not available for sale, but might be similar to a V100 in terms of computing power. A single PCI V100 costs about 10,000 Euros in Europe. But if you buy 5,000, you can certainly get a much cheaper price. Of course you also need the computers that host them, and the power supply (250W*5,000 = 1.25 MW).
This being said, I would not be surprised if their trained network could still beat Stockfish on ordinary hardware. And I expect deep-learning hardware will become much cheaper and commonplace in the future. Even cell-phones are starting to have deep-learning hardware now.
A distributed open-source effort might be enough to produce a super-strong network in a few months. This is what Gian-Carlo has started with Leela in Go. Maybe he'll do it for chess and shogi, too.
