New answers tagged

2

I'd like to add some reflections to the answers. First, we probably have to distinguish how chess is played by a chessplayer, computer, or mathematician. The main point here is that these three may use different criteria when making moves. The mathematician tries to optimize his or her game in general while a chessplayer or neural network may use local ...


6

Yes the characterization is correct, and there are 58,084,310 legal collections in total. To make headway, we need the right level of discourse, avoiding loss of accuracy while avoiding diving into trivialities. Necessity & sufficiency of the deletion moves Two kinds of operation were suggested to be necessary & sufficient to reach all legal ...


2

I'm very late but I am working on something similar. Here are are a couple of resources that involve using autoencoders. https://chessvschessproject.wordpress.com/ https://arxiv.org/abs/1711.09667 https://github.com/oripress/DeepChess Hope they help! Let me know how it goes.


2

If the board is given and only the source and target square, as well the promotion choice are considered (as in the UCI format), then it appears there will be 1968 possible moves. # Python # pip install python-chess import chess moves = 0 # Queen, covers all lines and diagonals for x in range(8): for y in range(8): board = chess.Board("8/8/...


3

The board layout can be repeated at most 11 times with White having the move, the 12th will be a draw. [FEN "rnbqkbnr/1pp2pp1/4p3/p2pP2p/P6P/8/1PPP1PP1/RNBQKBNR w KQkq d6 0 1"] 1. Be2 {White can no longer capture en passant.} Be7 2. Bf1 Bf8 {2nd time} 3. Be2 Be7 4. Bf1 Bf8 {3rd time} 5. Rh2 {White can no longer 0-0} Be7 6. Rh1 Bf8 {4th time} 7. ...


Top 50 recent answers are included