TalkChess.com

Hi Matthew, Thanks for sharing the project of Giraffe! I am just trying to replicate the experiments of training a NN evaluator for Giraffe. The first few iterations running looks fine. I just need to find a faster machine for more iterations (If just using i thread, a iteration will take 23 mins on...

Hi Gerd, thank your for the suggestions and links! Yes, I agree with you. After making this post I found that there are some more refined work like Matthew's Giraffe and DeepChess that has existed. The work on Deep Pink is still in an early stage IMO. Also thanks for all the comments and discussion ...

Hi Gerd, just realize that it is an old post from 2014. I saw it on Kaggle's facebook page, which was rebloged by Yhat three days ago. I guess the only thing "new" might be on the source code, where the author made some minor change until last spring.

Just found this blog post about deep learning in chess, by Erik Bernhardsson http://blog.yhat.com/posts/deep-learning-chess.html And the source code: https://github.com/erikbern/deep-pink It mentioned an engine "Deep-Pink", which includes a trained neural network model (for evaluation function). May...

Thank you very much for your reply, Daniel!

Hi Daniel, Just want to ask one more question about Scorpio by the way: is it possible to turn the code about SMP search off in Scorpio, but still keep the cluster search code? These days I am aslo trying to make a Scorpio-perft version running on the clusters. Turning the SMP search off might help ...

Hi Daniel, Thanks for you comment! I really learned a lot from Scorpio~ If you see the communication procedure of my program, it is actually almost the same as Scorpio. Firstly, a slave host randomly choose another host to ask “whether a help is needed” by sending OFFERHELP (which is just HELP msg i...

Hi all, Recently I am trying to write a MPI-based perft. I do this as an exercise of understanding the framework of the MPI-based parallel alpha-beta search. So I choose perft because it is relatively easier, and is also easy to verify the correctness. My program starts from Viper. The implementatio...

Hi all, The question came from an experiment that I did recently. I replace the evaluation function in Fruit 2.1 engine with the evaluation function of Sungrous 1.4. Let’s call this hybrid engine “Fruit-SungorusEval”. Here replace means I implement an evaluation function for Fruit 2.1 that always r...

Hello. I have done the same test with Andscacs. Andscacs with the evaluation of Sungorus easily outsearches Sungorus, obtaining 80% of the points. Here I put a file with the two executables, two pgn files, and a cutechess bat file I used to do the tests: www.andscacs.com/sungorus/sungorus.rar So I ...