| |
BGonline.org Forums
Huh?
Posted By: Maik Stiebler In Response To: Very impressive result from DeepMind team (Maik Stiebler)
Date: Wednesday, 13 December 2017, at 3:33 p.m.
I just noticed that you might wonder how I arrived at 26000. The relevant quote from the preprint is:
AlphaZero searches just 80 thousand positions per second in chess and 40 thousand 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 variations...
I wasn't aware just how sloppy the quoting in the Gizmodo article was.
| |
BGonline.org Forums is maintained by Stick with WebBBS 5.12.