Counterfactual Regret Minimization (AGT 26)

Поделиться
HTML-код
  • Опубликовано: 12 ноя 2024

Комментарии • 12

  • @kimchangjun5311
    @kimchangjun5311 Год назад +11

    Amazing step by step example for CFR !!!

  • @Robelseyoum-s2l
    @Robelseyoum-s2l 18 дней назад

    Wow amazing tutorial. Thanks ❤

  • @aptor
    @aptor 7 месяцев назад

    This is by far the best explained CFR lesson. Thank you for doing this!

  • @5th_Interaction
    @5th_Interaction 10 месяцев назад +1

    Beautifully articulated.

  • @ruairi-spain
    @ruairi-spain 7 месяцев назад +1

    More videos please! Great work, you make hard things easier to visualise. I hope you get back to making RUclips videos ❤

  • @michaelschoenhals376
    @michaelschoenhals376 9 месяцев назад +1

    thanks a ton for this! great video.

  • @Eddie-m7v
    @Eddie-m7v Месяц назад

    shouldn't folding have a utility or expected value of zero. since no money goes into the pot how can it return -1 in value?

  • @sounakmojumder5689
    @sounakmojumder5689 5 месяцев назад

    Hi, thank you do you have any pytorch application?

  • @bertobertoberto242
    @bertobertoberto242 Год назад +4

    DS student here, trying to grasp DeepCFR, amazing video... just wanted to point out a thing... the "P(K|Qb)" you say that you use Bayes rule and you phrase it like "P(P1 would play bet when they have a king)/P(P1 would play bet overall)"... I might be mistaking, but i don't see how you are applying Bayes... instead, I got your same result using the definition of conditional probability P(a|b) = P(a,b)/P(b)... because I get "P(KQb)/P(Qb)", now Q and b/K are independent events, so "[P(Kb)P(Q)]/[P(Q)P(b)]"... from here, applying the definition of joint probability and total probability, I get your same final probability
    Apart from this, thank you so much

    • @jonnyx850
      @jonnyx850 9 месяцев назад +1

      You're correct, he's not using baye's rule/thm. It's the definition of conditional probability in Bayesian stats that he's using. It's actually fairly common for people to mix them up. Nbd

    • @CsabaSzepesvari
      @CsabaSzepesvari 7 месяцев назад +1

      Some people actually say that Bayes' rule/thm = definition of conditional probability. In a way, they are not completely wrong:)

  • @julienescaig6317
    @julienescaig6317 7 месяцев назад

    You are fucking awesome Bro 🙏