MIT 6.S191 (2023): Reinforcement Learning

Поділитися
Вставка
  • Опубліковано 21 гру 2024

КОМЕНТАРІ • 72

  • @khalidalsaleh3858
    @khalidalsaleh3858 Рік тому +1

    Thanks!

  • @muhammadalikhan5003
    @muhammadalikhan5003 11 місяців тому +5

    Amazing lecture delivery. No words to thank you for sharing this wonderful resource for free. Thanks, MIT as well.

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @mehmetburakguldogan6815
    @mehmetburakguldogan6815 Рік тому +7

    Very good work. Seen many lectures on the topic but this is by far the best one and very intuitive. Thank you for sharing.

  • @RobertSaula
    @RobertSaula Рік тому +9

    Thank you so much! I loved the lecture, and I'm learning so much!
    Im only 16 now, but I hope I can one day get into MIT or another great university that teaches this well!

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

    • @AntonyNguyen-wy4tb
      @AntonyNguyen-wy4tb Місяць тому

      @@bohaningcoursesnap or coursnap

  • @franco-parra
    @franco-parra Рік тому +3

    Great lecture. To be precise, at 24:37, you propose the 'target' as a function of the best action a' in some state s', but you don't explicitly define where this s' comes from. I may be mistaken, but I believe that this s' essentially represents the state s in the next step (t+1), as demonstrated in ua-cam.com/video/wDVteayWWvU/v-deo.html (at 14:45). I hope this information is useful to someone.

  • @BehindTheBackground
    @BehindTheBackground 10 місяців тому +2

    Excellent slides and explanations!

  • @imZoox
    @imZoox Рік тому +5

    haha at 19:50, William Lin the CP legend is answering the question :D
    Its so weird, I am not even from the US neither I study there but I recognize a student from his voice at MIT in an MIT online lecture :D

  • @hilbertcontainer3034
    @hilbertcontainer3034 Рік тому +5

    ~wow my favorite area about AI =]
    cant wait to finish the lecture

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @cyrusmobini1321
    @cyrusmobini1321 Рік тому +8

    Great as always, thanks for being consistent

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @agenticmark
    @agenticmark 10 місяців тому

    Glad to see ML can figure out what I did as an 8 year old with a stack of quarters :D

  • @nageshwararaov118
    @nageshwararaov118 Рік тому +2

    Thank you very much. 😊

  • @pavalep
    @pavalep Рік тому +8

    Thanks for explaining complex Deep Learning and Reinforcement principles
    in a simplistic manner 🙌👍

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @xzuanaja2746
    @xzuanaja2746 Рік тому +13

    This is so great! but unfortunately due to my limited English, I didn't understand some parts. Hopefully in the future there will be subtitles in Indonesian or other languages, thank you very much!

    • @master7738
      @master7738 Рік тому +1

      you can use subtitles if you want

  • @smftrsddvjiou6443
    @smftrsddvjiou6443 Рік тому

    I recommend Barto Sutton „Reinforcement Learning“, 1st Edition, way,way better than the newer 2nd Edition.

  • @MrMonkeyMana
    @MrMonkeyMana Рік тому +3

    Can you teach AI to play City Skylines.

  • @prithvishah2618
    @prithvishah2618 Рік тому +2

    Thank you so much :)

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @seanwalsh358
    @seanwalsh358 Рік тому +1

    Great lecture from a great instructor.

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @SphereofTime
    @SphereofTime 7 місяців тому +1

    7:00

  • @nikteshy9131
    @nikteshy9131 Рік тому +6

    Wow, Thank very much you )) 🥰🥰😊

  • @sirabhop.s
    @sirabhop.s Рік тому +1

    Thank you so much

  • @esthertschache
    @esthertschache Рік тому

    Great video!

  • @jennifergo2024
    @jennifergo2024 Рік тому

    Thanks for sharing!

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @yuqiwang3296
    @yuqiwang3296 Рік тому +2

    great thanks for the course!❤

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @ReeceGao
    @ReeceGao Рік тому

    It is so clear. Thank you very much!

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @herikaniugu
    @herikaniugu Рік тому

    RL is so good for optimizing the trading strategies

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @SphereofTime
    @SphereofTime 7 місяців тому +1

    14:25

  • @saprogrammer2702
    @saprogrammer2702 Рік тому

    Dude, this guy did such a good job!!!!

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @vahidg1500
    @vahidg1500 Рік тому

    Thank You, Ostad Amini, But how can I find some code examples for policy learning like ppo?

  • @TheEgesko
    @TheEgesko Рік тому +1

    Great video! 🙏

  • @blas.duarte
    @blas.duarte Рік тому +1

    Great!

  • @Gabcikovo
    @Gabcikovo Рік тому +1

    54:38

  • @jiunyen5586
    @jiunyen5586 Рік тому

    Thanks for the thorough vid! I'm a bit lost @ 39:31 on where the "-0.8" velocity come from. The closest I'm trying to interpret is given the mean=-1 and var=0.5 the prob of norm dist at mean would be about 0.8... and since your going the negative direction to action a, then it becomes -0.8 ?? But this interpretation seems wrong since the mean should indicate the direction and velocity of action a, while the prob is for computing the loss. So.... what am I missing here? Thanks!

    • @gnikhil335
      @gnikhil335 Рік тому

      when you say " the prob of normal distribution at mean would be around 0.8" where did you get 0.8 from ? (the maximum value of this distribution is 0.564 at mean ) and secondly I think he is using 0.8 m/s as an example ( its a random value which you might get after mapping it back to a speed variable in your game )

    • @jiunyen5586
      @jiunyen5586 Рік тому

      @@gnikhil335 Good call! I misused that variance for std. My mistake. And I also really should've said likelihood there. But yeah, really I was just trying to figure out why he said the mean is centered at -0.8 but also shows a mean of -1 for the predicted params of pdf. As in are they just separate random examples or are we using a pdf with mean=-1, var=0.5 to determine the prob when speed is -0.8, which also doesn't seem likely since I thought we would use the velocity with the max likelihood (i.e. mean).

  • @MrPejotah
    @MrPejotah Рік тому +2

    Once again a great lecture. I have a challenge, and I wonder if you can help me. I'm currently implementing a NN to determine customer satisfaction through a set of inputs that translate behavioural patterns (think # of complaints with our customer service, rate of usage of our services, etc.), and I'd like to know how much each input i'm using contributes to the overall satisfaction score. I imagine this would involve performing the gradient of the output node (a single one in this case), to each input. Is there any lecture where you go into the details of this, both the math and tensorflow code? Thanks in advance!

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @kritsaphongphuthibpaphaisi1509

    Great lecture

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @DonReichSdeDios
    @DonReichSdeDios Рік тому

    An apple with a byte❤
    ✒️ fellow August 13th🤳🏿

  • @shojintam4206
    @shojintam4206 Рік тому

    33:13

  • @UmamahBintKhalid
    @UmamahBintKhalid Рік тому +8

    Oh my God, he is so Handsome. And your spoken, lecture delivery, and fluency in RL in as awesome as your looks are....🤩 focusing on the speaker more than the slides. May Allah Almighty bless you man

    • @bohaning
      @bohaning 10 місяців тому

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @madhusudhanreddy9157
    @madhusudhanreddy9157 Рік тому

    Hi Alex,
    Could you please suggest any best platform(online coding) that works properly for Reinforcement Learning, In our local systems, are getting errors(system dependencies).
    Even google colab is showing error when using gym library
    Thanks
    Your UA-cam Follower

    • @xpcalc446
      @xpcalc446 Рік тому

      Have you try to solve those errors by installing the the correct version of the packages?

    • @bohaning
      @bohaning 10 місяців тому +1

      Hey, I'd like to introduce you to my AI learning tool, Coursnap, designed for youtube courses! It provides course outlines and shorts, allowing you to grasp the essence of 1-hour in just 5 minutes. Give it a try and supercharge your learning efficiency!

  • @Achielezz
    @Achielezz 11 місяців тому

    You say state-action-pear but show an apple, I AM CONFUSION! AMERICA EXPRAIN! :) Loved the lecture, really well done.

  • @pravachanpatra4012
    @pravachanpatra4012 Рік тому

    16:03

  • @SantoshKumar-hx2ig
    @SantoshKumar-hx2ig Рік тому

    Lecture 7 ?

    • @AAmini
      @AAmini  Рік тому

      Lecture 7 is having some technical difficulties so it will be published tomorrow same time (10am ET) -- sorry for the delay!

    • @SantoshKumar-hx2ig
      @SantoshKumar-hx2ig Рік тому +1

      @@AAmini I am very happy for reply within few minutes.
      Today I feel the power of mit .

    • @AAmini
      @AAmini  Рік тому

      Thank you for your understanding :)

  • @ojasvisingh786
    @ojasvisingh786 Рік тому +3

    👏👏

  • @smftrsddvjiou6443
    @smftrsddvjiou6443 Рік тому

    Now, he knows that Q values can be converted into Probability?

  • @roadto300kusdbtc7
    @roadto300kusdbtc7 Рік тому

    once again, audio is super quiet. Had to turn the volume to 100. Fire the audio guy lol

  • @davidkamran9092
    @davidkamran9092 Рік тому

    SEALCLATCONTITOIN - YALL NEED TO INCORPORATE HARD-CODED TRAJETORIES LIKE POLITICAL VIEWS IN DEEP LEARNING .. THE SYSTEM DYNAMICS CHANGE BASED ON POLITICAL MODALITIES