In my game[0] it played well until it hit a position where it seemed to run out of ideas. At that point, it let me take its queen for a rook. The strange thing was that it felt like playing my five year old, who also plays well until he runs out of ideas and then just sacrifices a piece.<p>It also missed the kind of tactics that my kid misses and played surprisingly human like mistakes. Note move 35... Rxf2, as if it forgot about the bishop because it had moved to the other end of the board. That's the kind of mistake a human player might make and computers never do.<p>It strikes me that this would be a great engine for my five year old to practice against. I'd love to see it added to lichess or put into a phone app for that purpose.<p>0. <a href="http://en.lichess.org/beOA0Q2T#68" rel="nofollow">http://en.lichess.org/beOA0Q2T#68</a>
Hello, I'm the creator of spawkfish :)<p>The project is still in pretty early stages, so don't expect it won't take down any strong chess players yet, but I'm hoping that with a bit of effort it will be possible for neural networks to do for chess what they have recently done for Go.
That was really impressive. Other than playing very accurately, I felt it played far more human-like than most computer chess engines.<p>I've written several chess engines, and have often wondered for some time whether or not there was a chance for a more AI/pattern-driven approach.<p>Are you using your AI just for evaluation? E.g. do you have a traditional PVS/negascout (or similar) search? Presumably an 'extreme Type C' (no search) would fail to recognise various draws (50 move/repetition)?<p>Good work :-)
I won :)<p>4R2k/p5p1/7p/n4Q2/7q/2PP1P2/Pr3P1P/5RK1 b - - 6 27<p>EDIT - for context, I was about 1900 USCF in my prime 20 years ago - still do puzzles daily.<p>In any case, I think this is cool. I was also surprised it managed to play efficiently given the load you must be feeling from HN. Thanks for making this and showing it!
Normally against a chess computer, you try to play positionally and avoid tactical situations - i.e. you avoid its strengths and target its (relative) weakness.<p>It is nice (and also rather uncanny) to be in the opposite situation here. Positionally it looks good, tactically, not so good.<p>A great project!
Seems very interesting, I really think these approaches will work rather well on a variety of games. Very exciting times. Btw, there is another already Open Source Neural Network Chess engine that might be worth exploring for similar ideas. That codebase already has a minmax search based on the network evaluation. Paper is at: <a href="http://arxiv.org/abs/1509.01549" rel="nofollow">http://arxiv.org/abs/1509.01549</a> Code is at: <a href="https://bitbucket.org/waterreaction/giraffe" rel="nofollow">https://bitbucket.org/waterreaction/giraffe</a>
You can play against the bot online at <a href="http://spawk.fish/play/" rel="nofollow">http://spawk.fish/play/</a><p>I lost, but I'm bad at chess.
Very nice! The only thing missing is a Back button to allow me to back out of mistakes. :-)<p>I believe that chess follows the state of the art in AI. The first wave of success was based on brute force of computing better than people. Now it's harnessing insight. Keep up the interesting work!
Very nice! It may be annoying, but I think at some point you really will need to keep track of castling rights and en-passant (position repetition is much harder but I don't think it is so necessary). Some evaluations depend very heavily on them.
I won (hardly, after I had 3 pawns against a knight during mid game) and I don't think I'd reach 1600 elo if I were to play in tournaments. My elo is about 1620 on chesstempo, where I solve tactics quite often (daily, during the last 8 weeks or so)