WU-UCT
WU-UCT copied to clipboard
A novel parallel UCT algorithm with linear speedup and negligible performance loss.
I'm interested your paper. However, I feel your key idea is same as the virtual loss for MCTS parallelization? what's the difference between them? Hope for your answer. Best wishes
The code can not work when there are two or more WU-UCT players in one game 。
in my opinion, the way choosing an action to expand is purely based on the prior probability or just random choice. So why there is a while loop? I don't...