[xoroshiro]

Does this mean it learns what to search? I wonder why they thought it was a good idea. I thought the whole point of MC was that pruning algorithms like the ones in chess wouldn't work for a larger search space.

[letlambda]

The policy network is a function from board states to a scoring of moves. The policy network with the greedy heuristic, ie pick the highest rated move with no explicit look ahead method, plays at a high amateur level.

This was... unexpectedly good.

It effectively reduces the branching factor of Go from the number of moves available, to the number of moves actually worth considering.

[shmageggy]

That's what the policy is. Given a board state, the policy gives you a distribution over all available moves.