Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Nit: Chess requires more than the state of the board. #314

Open
BasedLukas opened this issue Jan 26, 2024 · 0 comments
Open

Nit: Chess requires more than the state of the board. #314

BasedLukas opened this issue Jan 26, 2024 · 0 comments

Comments

@BasedLukas
Copy link

From your excellent writeup (thank you!):

History of State: Since Go is not completely observable from the current state of the board, the neural network also takes as input the boards from the last 7 time steps. This is a feature of the game itself, and other games such as Chess and Othello would only require the current board as input.

This is not strictly speaking true, as chess also requires knowledge of the previous states of the board, to determine for example if castling is permitted, or if you may capture en passant amongst others.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant