If you look at the latest TCEC Superfinal, game 1, you can see that Stockfish evaluated about 120 million positions per second. TCEC’s CPU engines run on 88 physical cores. The world’s fastest supercomputer right now has, if I am not mistaken, about 8 million cores.
How many moves does AlphaZero calculate?
According to Deep mind’s article, Alpha Zero searches roughly 10,000 moves per decision, while Stockfish is around 10,000,000 moves.
Did AlphaZero really beat stockfish?
After four hours of training, DeepMind estimated AlphaZero was playing chess at a higher Elo rating than Stockfish 8; after 9 hours of training, the algorithm defeated Stockfish 8 in a time-controlled 100-game tournament (28 wins, 0 losses, and 72 draws). The trained algorithm played on a single machine with four TPUs.
Which is better stockfish or AlphaZero for chess?
The hardware that ran Stockfish, as I pointed out, was at the very best 18 times faster than mine (Update: on a single core) based on the move I analyzed. I’m not sure if AlphaZero could really make use of such hardware to train its networks in 4 hours, I can only assume it’s too low for a game like chess.
How does AlphaZero compare to Monte Carlo search?
Comparing Monte Carlo tree search searches, AlphaZero searches just 80,000 positions per second in chess and 40,000 in shogi, compared to 70 million for Stockfish and 35 million for elmo. AlphaZero compensates for the lower number of evaluations by using its deep neural network to focus much more selectively on the most promising variation.
How is the performance of stockfish dependent on hardware?
As I said, the performance of Stockfish (and AlphaZero) is dependent on the hardware as well as the time limit. For Instance, if we gave Stockfish more hardware (and AlphaZero less) and regenerated that figure, its line could be transformed such that it always stays above the AlphaZero line.
How many wins and losses does AlphaZero have?
In a 1000-game match, AlphaZero won with a score of 155 wins, 6 losses, and 839 draws. DeepMind also played a series of games using the TCEC opening positions; AlphaZero also won convincingly. Stockfish needed 10-to-1 time odds to match AlphaZero. Similar to Stockfish, Elmo ran under the same conditions as in the 2017 CSA championship.
