News for hackers. Stuff that matters.
Re:Show HN: Easily train AlphaZero-like agents on any enviro... by s-casci on Wednesday December 20, 2023 @03:28PM (#38713196)
The policy function outputs the probability of taking every possible (legal or illegal) action. Once you have a way of indexing those actions, both the policy and the game need to refer to the same thing when indexing the same number

There are no comments on this comment yet.