Sunday, September 8, 2019

In re-enforcement learning we deal with infinite sequences of actions.   We thus need to learn how think on their probability  https://drive.google.com/file/d/1NuG-od_-ogOSsakQeJpDDtK3nwzpC5LZ/view?usp=sharing.
at

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

  Our next ML study group meeting will take place on Monday the 8 th  of October.   I'll cover the contraction theorem.   See relevant s...

  • (no title)
    Ml crash directory Are you familiar with regression - https://m.youtube.com/watch?v=aq8VU5KLmkY ?  One way to view Ml is regression on ster...
  • (no title)
    We'll cover LDA in tw's meeting.   Here is the slide - https://drive.google.com/open?id=1KRoCA4vo9H9oJOl3iD-qRqIHl9qQq9vf This is ...
  • (no title)
    Whiteboard from today's meeting on Bayesian ML: Cox:  P(A, B) = P(A|B)P(B) = P(B|A)P(A) => P(A|B) = [P(B|A)P(A)] / P(B) (Bayes) ...