If that's true, then it's time for a fair tournament between AZ and Stockfish:ġ) Both engines should have equal hardware support. Still, alpha-zero evaluates the position better and predicts a better move than stockfish. If you want to see the real strength of Alpha Zero, both should be allowed to evaluate an equal number of positions. The difference will become as large as human vs machine. If you say, stockfish was running on some low end machine and need the even more stronger machine, you are giving more power to stockfish and the difference ratio will increase even more. One more thing, Stockfish was running on 32 cores machine and was evaluating 875 positions or moves when alpha zero was only able to evaluate 1 position (70 millions / 80K). Unfortunately, I don't have enough resources to get the answer. I am also interested to see, if we let it play (train) against stockfish in self-learning mode, how long it will take to get the strength of Google's alpha-zero.
#Stockfish chess make ai faster code#
I hope would have enough resources to test this code on GPUs and let it train for atleast 2 days and then let it play against stockfish and evaluate the strength. Little older style like alphaGo where policy and value use to have separate neural network unlike google alpha zero where both are combined. I have tested it out, it is a good working code. There is an interesting code for reinforcement learning chess available on github at Amazingly, some of its games remain quite meaningful to us limited mortals.Įven if Google does not open up his Alpha-zero, we can still evaluate the strength of Alpha Zero What AlphaZero probably does is play the best chess moves that have ever been seen. This does not matter so much when comparing conventional engines, because (extrapolating enthusiastically from a little data, backed up with some theoretical facts) they improve at a similar rate with computational resources (the reason this is to be expected is that they come from a similar heritage of alpha-beta search and pseudo-materialistic positional evaluation). That does not make that engine the best player: that makes that engine a better player only when its opponent is handicapped to play more weakly: the games played would not be of such high quality, and thus not so interesting. Note also that it could well be that there is some type of equitable restriction that makes another engine better than AlphaZero.
The point of AlphaGo was to be the best chess player, not the best chess player with an arbitrary handicap.
#Stockfish chess make ai faster upgrade#
Sorry, but the only interesting change is to upgrade Stockfish's hardware as much as desired.
0 kommentar(er)
