From the AlphaZero paper:

The input to the neural network is an N × N × (M T + L) image stack that represents state using a concatenation of T sets of M planes of size N × N . Each set of planes represents the board position at a time-step t − T + 1, ..., t, and is set to zero for time-steps less than 1

From the original AlphaGo Zero paper:

Expand and evaluate (Figure 2b). The leaf node $s_L$ is added to a queue for neural network evaluation, $(d_i(p), v) = f_\Theta(d_i(s_L))$, where $d_i$ is a dihedral reflection or rotation selected uniformly at random from i∈[1..8]

Ignoring the dihedral reflection, the formula in the original paper $f_\Theta(s_L)$ implies that only the board corresponding to $s_L$ is passed to the neural network for evaluation when expanding a node in MCTS, not including the 7 boards from the 7 previous time steps. Is this correct?


Your Answer

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

Browse other questions tagged or ask your own question.