MIT 6.S191 (2023): Reinforcement Learning

Рет қаралды 136,600

Күн бұрын

Пікірлер: 72

@mehmetburakguldogan6815 Жыл бұрын

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

@muhammadalikhan5003 10 ай бұрын

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

@bohaning 10 ай бұрын

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!

@RobertSaula Жыл бұрын

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 10 ай бұрын

@AntonyNguyen-wy4tb 26 күн бұрын

@@bohaningcoursesnap or coursnap

@cyrusmobini1321 Жыл бұрын

Great as always, thanks for being consistent

@bohaning 10 ай бұрын

@hilbertcontainer3034 Жыл бұрын

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

@bohaning 10 ай бұрын

@BehindTheBackground 9 ай бұрын

Excellent slides and explanations!

@pavalep Жыл бұрын

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

@bohaning 10 ай бұрын

@xzuanaja2746 Жыл бұрын

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 11 ай бұрын

you can use subtitles if you want

@agenticmark 9 ай бұрын

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

@franco-parra 11 ай бұрын

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 kzbin.info/www/bejne/rXW5pZiXrryKrLc (at 14:45). I hope this information is useful to someone.

@imZoox Жыл бұрын

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

@saprogrammer2702 Жыл бұрын

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

@bohaning 10 ай бұрын

@nageshwararaov118 Жыл бұрын

Thank you very much. 😊

@smftrsddvjiou6443 11 ай бұрын

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

@seanwalsh358 Жыл бұрын

Great lecture from a great instructor.

@bohaning 10 ай бұрын

@herikaniugu Жыл бұрын

RL is so good for optimizing the trading strategies

@bohaning 10 ай бұрын

@prithvishah2618 Жыл бұрын

Thank you so much :)

@bohaning 10 ай бұрын

@sirabhop.s Жыл бұрын

Thank you so much

@yuqiwang3296 Жыл бұрын

great thanks for the course!❤

@bohaning 10 ай бұрын

@jennifergo2024 11 ай бұрын

Thanks for sharing!

@bohaning 10 ай бұрын

@ReeceGao Жыл бұрын

It is so clear. Thank you very much!

@bohaning 10 ай бұрын

@TheEgesko Жыл бұрын

Great video! 🙏

@khalidalsaleh3858 Жыл бұрын

Thanks!

@blas.duarte Жыл бұрын

Great!

@nikteshy9131 Жыл бұрын

Wow, Thank very much you )) 🥰🥰😊

@esthertschache 11 ай бұрын

Great video!

@kritsaphongphuthibpaphaisi1509 Жыл бұрын

Great lecture

@bohaning 10 ай бұрын

@MrMonkeyMana Жыл бұрын

Can you teach AI to play City Skylines.

@Gabcikovo Жыл бұрын

54:38

@Achielezz 10 ай бұрын

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

@SphereofTime 7 ай бұрын

14:25

@vahidg1500 Жыл бұрын

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

@MrPejotah Жыл бұрын

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 10 ай бұрын

@SphereofTime 7 ай бұрын

7:00

@DonReichSdeDios Жыл бұрын

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

@jiunyen5586 Жыл бұрын

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 Жыл бұрын

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 Жыл бұрын

@@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).

@ojasvisingh786 Жыл бұрын

👏👏

@shojintam4206 Жыл бұрын

33:13

@UmamahBintKhalid Жыл бұрын

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 10 ай бұрын

@madhusudhanreddy9157 Жыл бұрын

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 KZbin Follower

@xpcalc446 Жыл бұрын

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

@bohaning 10 ай бұрын

@pravachanpatra4012 Жыл бұрын

16:03

@smftrsddvjiou6443 11 ай бұрын

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

@SantoshKumar-hx2ig Жыл бұрын

Lecture 7 ?

@AAmini Жыл бұрын

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

@SantoshKumar-hx2ig Жыл бұрын

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

@AAmini Жыл бұрын

Thank you for your understanding :)

@roadto300kusdbtc7 Жыл бұрын

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

@davidkamran9092 Жыл бұрын

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