Re:Multiplayer AlphaZero
by Mageek on Wednesday October 30, 2019 @11:30AM
(#21398806)
Nice and concise paper. All that changed was outputting a vector of predicted game values, as we go from having a zero-sum game with two players (which can be summarized with a single value) to a game with n players. Makes sense.
The comparison against MCTS shows strong performance from AlphaZero. Would be curious to see the performance of AlphaZero vs. number of its own rollouts - ie is the probability head output alone already encoding enough information to play well, and how deep does it have to look ahead to determine good play. Finally, for tic-tac-mo and connect 3x3, it should be possible to determine the optimal move. How much training / lookahead is required to achieve that? Does AlphaZero achieve perfect play for these games?
The paper's first listed contribution is "an independent reimplementation of DeepMind's AlphaZero algorithm". Maybe I missed it, but I don't see a link to a repo with the implementation.
The comparison against MCTS shows strong performance from AlphaZero. Would be curious to see the performance of AlphaZero vs. number of its own rollouts - ie is the probability head output alone already encoding enough information to play well, and how deep does it have to look ahead to determine good play. Finally, for tic-tac-mo and connect 3x3, it should be possible to determine the optimal move. How much training / lookahead is required to achieve that? Does AlphaZero achieve perfect play for these games?
The paper's first listed contribution is "an independent reimplementation of DeepMind's AlphaZero algorithm". Maybe I missed it, but I don't see a link to a repo with the implementation.