• @[email protected]OP
      link
      fedilink
      4
      edit-2
      7 months ago

      In the case of Google/DeepMind’s SIMA it is an instruction-following agent for simpler, but menial tasks in a game. It is particularly not autonomous, and has no notion of reward. And what is being used is a modified behavior cloning with a text-conditioned policy network.

  • @x4740N
    link
    English
    47 months ago

    You don’t play goat simulator, it’s a customizable experience

  • @[email protected]
    link
    fedilink
    2
    edit-2
    7 months ago

    So what. It can play “games it had never seen before” but at the same time “by watching human players”?