Deep RL Bootcamp Lecture 2: Sampling-based Approximations and Function Fitting

Поделиться
HTML-код
  • Опубликовано: 17 янв 2025

Комментарии • 15

  • @jorgelarangeira7013
    @jorgelarangeira7013 6 лет назад +31

    Very good lecture, overall. Unfortunately, the flow gets interrupted too often by questions from the audience -- which also eat up time. By the end, lecturer is having to rush through some complex topics (TD learning, policy iteration) that would have required more in-depth explanations.

  • @ufukylmaz7628
    @ufukylmaz7628 22 дня назад

    Thanks a lot for sharing this great lecture.

  • @JoshVarty
    @JoshVarty 7 лет назад +8

    Great lecture! Thanks for putting these up.

  • @alizafari8729
    @alizafari8729 4 года назад

    On 39:40 there is a great intuition on how epsilon-greedy chooses between exploration and exploitation.

  • @ProfessionalTycoons
    @ProfessionalTycoons 6 лет назад +1

    I like his presentation style.

  • @kargarisaac
    @kargarisaac 7 лет назад +3

    Great lecture! what is the address of Piazza for this bootcamp?

  • @adilahsan4448
    @adilahsan4448 6 лет назад +1

    Thank you so much for sharing these lectures... These are really helpful... :)

  • @lordleoo
    @lordleoo 2 года назад

    anyway to access those labs?
    there's no way we'd fully understand these algorithms, and get insights, and notice the small details, without actually writing our own code or playing with well written code

  • @mrbonzzai
    @mrbonzzai 6 лет назад

    Thank you for these lectures!! They are great!

  • @feifeizhang7757
    @feifeizhang7757 2 года назад

    ❤good content

  • @liangwang2688
    @liangwang2688 6 лет назад

    Thank you for the Great lecture!

  • @vadrif-draco
    @vadrif-draco Год назад

    Great lecture, but the last 10 minutes feel very rushed in my humble opinion...

  • @pengyuewang93
    @pengyuewang93 5 лет назад +1

    Too many questions!!!!

  • @dg404null
    @dg404null 8 месяцев назад

    厉害噢 深圳中学的学霸!