• INeedMana@lemmy.world
    link
    fedilink
    English
    arrow-up
    12
    ·
    10 months ago

    It’s cool but my question is (I did not see this addressed in the article nor video but might have missed it) did it learn to win the game in general terms or only this one example? I mean, if the layout of the board was changed, would it still solve it?

      • INeedMana@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        10 months ago

        Yes, but that’s kind of my point

        We see it learn something with insane precision but most often it is almost an effect of over-training. It probably would require less time to learn another layout but it’s not learning the general rules (can’t go through walls, holes are bad, we want to get to X), it learns the specific layout. Each time a layout changes, it would have to re-learn it

        It is impressive and enables automation in a lot of areas, but in the end it is still only machine learning, adapting weights to specific scenario

    • indomara@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      10 months ago

      It did learn to use shortcuts to skip parts of the maze, and had to be told not to. Super interesting!

      • INeedMana@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        ·
        10 months ago

        Yes, but that’s only because a generation found some random, specific motion that scored better. Not because it analyzed that doing a skip should be possible