• petrol_sniff_king@lemmy.blahaj.zone
    link
    fedilink
    English
    arrow-up
    8
    ·
    5 months ago

    When games that are losses for the AI from humans are included, the bug is fixed.

    You’re not grasping the fundamental problem here.

    This is like saying a calculator understands math because when you plug in the right functions, you get the right answers.

    • iopq@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      arrow-down
      4
      ·
      5 months ago

      The AI grasps the strategic aspects of the game really well. To the point that if you don’t let it “read” deeply into the game tree, but only “guess” moves (that is, only use the policy network) it still plays at a high level (below professional, but strong amateur)

      • petrol_sniff_king@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        7
        arrow-down
        1
        ·
        5 months ago

        How does it “understand the strategic aspects of the game really well” if it can’t solve problems it hasn’t seen the answers to?

        • iopq@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          arrow-down
          4
          ·
          5 months ago

          It doesn’t get fed answers in the training data, only positions. If it sees a position, it will eventually learn to solve it by itself