question on parallel tree search

[lcwd2]

AGZ uses virtual loss to make the tree search threads explore different paths. What is the strategy used in AlphaZero.jl?

[jonathan-laurent]

AlphaZero.jl does not have multiple workers explore the same MCTS tree and therefore there is no need for a virtual loss. Instead, many games are simulated in parallel during self-play and network inference requests are batched across those.

[lcwd2]

We probably still want a mechanism for matches to facilitate a large number of simulations.

[jonathan-laurent]

This is true and as a matter of fact, matches would be quite slow with the current implementation. This is on my TODO list though.

[lcwd2]

looking forward to the new release