>> In fact, less than two months later, DeepMind published a preprint of a third paper, showing that the algorithm behind AlphaGo Zero could be generalized to any two-person, zero-sum game of perfect information (that is, a game in which there are no hidden elements, such as face-down cards in poker).<p>I can't find this claim in the linked paper. What I can find is a statement that AlphaZero has demonstrated that 'a general-purpose reinforcement learning algorithm can achieve, <i>tabula rasa</i>, superhuman performance across many challenging domains'.<p>Personally, and I'm sorry to be so very negative about this, but I don't even see the "many" domains. AlphaZero plays three games that are very similar to each other. Indeed, shoggi is a variant of chess. There are certainly two-person, zero-sum, perfect-information games with radically different boards and pieces to either Go, or chess and shoggi - say, the Royal Game of Ur [1], or Mancala [2], etc, not to mention stochastic games of perfect information, like backgrammon, or assymetric games like the hnefatafl games [3], and so on.<p>Most likely, AlphaZero <i>can</i> be trained to play many such games very powerfully, or at a superhuman level. The point however is that, currently, <i>it hasn't</i>. So no "demonstration" of general game-playing has taken place, and of course there is no such thing as some sort of theoretical analysis that would serve as proof, or indication, of such ability in any of the DeepMind papers.<p>I was hoping for less ra-ra cheerleading from the New Yorker, to be honest.<p>________________<p>[1] <a href="https://en.wikipedia.org/wiki/Royal_Game_of_Ur" rel="nofollow">https://en.wikipedia.org/wiki/Royal_Game_of_Ur</a><p>[2] <a href="https://en.wikipedia.org/wiki/Mancala" rel="nofollow">https://en.wikipedia.org/wiki/Mancala</a><p>[3] <a href="https://en.wikipedia.org/wiki/Tafl_games" rel="nofollow">https://en.wikipedia.org/wiki/Tafl_games</a>