Stockfish versus AlphaZero
editIn December 2017, Stockfish 8 was used as a benchmark to evaluate Google division Deepmind's AlphaZero, with each engine supported by different hardware. AlphaZero was trained through self-play for a total of nine hours, and reached Stockfish's level after just four.[1][2] Stockfish was allocated 64 threads and a hash size of 1 GB; AlphaZero was supported with four application-specific TPUs. Each program was given one minute's worth of thinking time per move.
In 100 games from the normal starting position AlphaZero won 25 games as White, won 3 as Black, and drew the remaining 72, with 0 losses.[3] AlphaZero also played twelve 100-game matches against Stockfish starting from twelve popular openings for a final score of 290 wins, 886 draws and 24 losses, for a point score of 733:467.[4][note 1] The research has not been peer reviewed and Google declined to comment until it is published.[3]
In response to this, Stockfish developer Tord Romstad commented, "The match results by themselves are not particularly meaningful because of the rather strange choice of time controls and Stockfish parameter settings: The games were played at a fixed time of 1 minute/move, which means that Stockfish has no use of its time management heuristics (lot of effort has been put into making Stockfish identify critical points in the game and decide when to spend some extra time on a move; at a fixed time per move, the strength will suffer significantly). The version of Stockfish used is one year old, was playing with far more search threads than has ever received any significant amount of testing, and had way too small hash tables for the number of threads. I believe the percentage of draws would have been much higher in a match with more normal conditions."[6]
Grandmaster Hikaru Nakamura also showed skepticism of the significance of the outcome, stating "I don't necessarily put a lot of credibility in the results simply because my understanding is that AlphaZero is basically using the Google super computer and Stockfish doesn't run on that hardware; Stockfish was basically running on what would be my laptop. If you wanna have a match that's comparable you have to have Stockfish running on a super computer as well."[6]
{{credit d'auteur|interne|stockfish}}
- ^ Knapton, Sarah; Watson, Leon (6 December 2017). "Entire human chess knowledge learned and surpassed by DeepMind's AlphaZero in four hours". Telegraph.co.uk. Retrieved 6 December 2017.
- ^ Vincent, James (6 December 2017). "DeepMind's AI became a superhuman chess player in a few hours, just for fun". The Verge. Retrieved 6 December 2017.
- ^ a b "'Superhuman' Google AI claims chess crown". BBC News. 6 December 2017. Retrieved 7 December 2017.
- ^ "DeepMind's AlphaZero crushes chess". chess.com. 6 December 2017. Retrieved 13 December 2017.
- ^ Silver, David; Hubert, Thomas; Schrittwieser, Julian; Antonoglou, Ioannis; Lai, Matthew; Guez, Arthur; Lanctot, Marc; Sifre, Laurent; Kumaran, Dharshan; Graepel, Thore; Lillicrap, Timothy; Simonyan, Karen; Hassabis, Demis (5 December 2017). "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm". arXiv:1712.01815 [cs.AI].
- ^ a b "AlphaZero: Reactions From Top GMs, Stockfish Author". chess.com. 8 December 2017. Retrieved 13 December 2017.
Cite error: There are <ref group=note> tags on this page, but the references will not show without a {{reflist|group=note}} template (see the help page).