Physics Math be like…

  • LeFrog@discuss.tchncs.de
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    4 months ago

    Its about a certain form of reinforced learning, called Temporal Difference Learning:

    https://inria.hal.science/hal-00840470/document at page 11.

    The calculation is called simple because it follows directly from the definitions above. Simple means more like “follows directly from definition without fancy math tricks”, not " everyone who can read could solve this in 10 minutes".

    I think this is also mostly math related, not physics?

    I had a good laugh anyway. Good meme

    • bluemellophone@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      4 months ago

      Reinforcement learning is a machine learning (ML) technique (“AI” in layman terms) for optimizing neural networks and other types of non-linear models.

      As far as ML math goes, this is fairly tame. It looks complicated, but is spelled out clearly in the paper. A lot of these kind of theoretical papers — things that would get published in Automatica — are going to lean very heavy on math.

      Source: PhD in Computer Science with dissertation using neural networks.