"The final 9 planes encode possible underpromotions for pawn moves or captures in two possible diagonals, to knight, bishop or rook respectively. Other pawn moves or captures from the seventh rank are promoted to a queen." Doesn't this mean that the network does not know that it can promote to a queen?


It means that there is no explicit coding of action choices to promote to queen, it is the default assumption if the underpromotion actions are not taken.

The Alpha Zero chess implementation can represent promotion to queen by not selecting an underpromotion action, whilst moving a pawn so that it qualifies for promotion.

| improve this answer | |
  • $\begingroup$ This is the right answer. $\endgroup$ – hisairnessag3 Aug 13 '19 at 6:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.