Model Based Reinforcement Learning: Policy Iteration, Value Iteration, and Dynamic Programming

[@yiyangshao2003]

This is just awesome, especially for an undergraduate without much pre-knowledge about machine learning.Many thanks from a Chinese freshman.

[@yiyangshao2003]

Relationship between different concepts always confuses me, but your video explained it in a explicit diagram and this really helpes me a lot. Feeling really thrilled.Thanks again!

[@ghazal246486]

I've watched other lectures on RL before, I can understand the formulas much better now, the way you explain formulas is brilliant, you're a wonderful math lecturer

[@micknamens8659]

16:55 The value iteration function (VI) differs slightly from Bellman's equation (BE) because VI uses max on a (hence uses a single value), whereas BE uses max on all pi. Because pi is a probabilistic function, i.e. is yielding a specific action value 'a' with a certain probability, VI would need to have another level of summation over a multiplying the terms by pi(s,a). 20:05 Here we construct pi(s,a) as the argmax of VI. This means we set pi(s, argmax(s))=1, and pi(s, a')=0 for all other values a' /= argmax(s). This means pi(s,a) is deterministic, instead of probabilistic.

[@chandhru08]

This series really helps to understand the RL mechanisms. Thanks a ton for effort! Showing heart gesture unintentionally 21:35 😀

[@huyvuquang2041]

At 3:57, I think the R(s', s, a) function you are referring to is the "reward function", which returns the "Immediately reward (r) if you are at stage (s) and do the action (a) which lead to stage (s')". That would make more sense than "returning a PROBABILITY of a reward (r) given (s, a and s')". I saw this in your book also but cannot find this kind of function anywhere else. All other resources I found, when talking about this function R, that means the "immediately reward" of doing action a given stage s and new stage s', NOT the "probability of the reward". Later on in the clip, when you uses it in value function, I also see you use it as a mean for measuring the "Value of reward", not the "Probability of reward", therefore I think this might really be a mistake or something. If I'm getting it wrong somewhere, please help me clear my thought. I'm just being curious. Love your great work.

[@fredflintstone7924]

i love the way you explain it through the formula's most experts tell you the formula then go to an actual case, which leaves the learner disconnected from the math, thanks!

[@august4633]

Thank you so much. I've watched a lot of videos and didn't fully get these concepts for some reason. Now I think I finally get it. You're a great teacher.

[@aaroncollinsworth9365]

I actually feel smarter after watching this. Excellent video on all fronts!

[@samueldelsol8101]

your videos are increadibly well thought out and very educational, I should have known about them sooner. greetings from Munich, Germany!

[@borneoland-hk2il]

wow... just wow.. i'm amaze sir with your explanation that i really need. please keep the good work sir.

[@Moonz97]

Love this series! Hoped the video to go on and on but it ended too quickly. Can't wait for the next part! Keep up the great work :)

[@Eigensteve]

Thanks so much!!

[@adinovitarini6173]

Thank you Prof! this video really helpful to classify RL's methods. I really appreciate your diagram and your explanation.

[@Eigensteve]

Thanks -- glad it is helpful!

[@suri6294]

SUPERBBBBBB! Now I understand every inch of the research paper I was reading. Thanks!!!!

[@matthewchunk3689]

This is an excellent companion to your book. Thanks for both!

[@kevinchahine7553]

Thank you for making these videos. I'm learning so much! You are such a great explainer.

[@RasitEvduzen]

Optimal control, Control Theory, Reinforcement Learning, Machine Learning, System Theory, System Identification are intellectual banquet.

[@mariogalindoq]

Beautiful. Please continue. Will you explain algorithms like PPO, TD3, DDPG, etc.? If so, I will appreciate each one. Also, it will be very interesting if you can give your opinion on some RL libraries like ray/RLlib, baselines3, etc. I know that this may be much more than what you are thinking of including in this course, but I do not lose anything by suggesting those topics to you :) Thank you.

[@Eigensteve]

Great suggestions! I will think about how to add these in the future. Might need to be in a future filming session, since it might take some time.

[@superuser8636]

PPO would be very welcome. Deep RL is big now. Thanks for your videos, Dr. Long time fan

[@cisimon7]

Good suggestion, hope we get videos on those soon

[@asier6734]

Very well structured and layed out, clearly explained, thank you

[@NaveenKumar-yu3vw]

Thank you for simplifying a lot of things. I had read corresponding chapters from Sutton and Barto book but I got more clarity on practical aspects from this video.

[@nj4089]

Thank you so much. Really appreciated the explanation at 24:20

[@AliRashidi97]

Tnx a lot professor Brunton! You're creating great materials!

[@AnnieBhalla]

probably the best explanation

[@paaabl0.]

Great and clear explanation, Steve! Thank you.

[@jimklm3560]

In 8:20, shouldn't we have considered all the possible states s1=s' we can possibly end up when we follow a policy π?

[@azadarashhamn]

Another great work. Thanks again.

[@minapagliaro7607]

great video thank you for your contribution 🎉

[@mohammadsalah2307]

Could you possibly explain more about "policy iteration and value iteration, leading to the quality function"? 25:40. Specifically, what is "redundant"? I believe there is a mistake. Here Q(s, a) and V_\pi(s) seem to have exactly the same formation. I still did not understand how this lead to the conclusion that quality function allows us to enable "model-free learning". I think the correct formula for Q is : Q(\mathbf{s}, \mathbf{a})=\mathbb{E}\left(R\left(\mathbf{s}^{\prime}, \mathbf{s}, \mathbf{a} ight)+\gamma Q\left(\mathbf{s}^{\prime}, a ight) ight) By the way, I am also a little confused about what is the "model" of the future reward is? 25:10

[@danielmilyutin9914]

I love the way you give the material. Became curious about how do you project those formulae onto screen and able to see them? Is it glass screen and projector on side of camera? Or is it special screen?

[@samirelzein1095]

now i know i ll understand well RL when you ll explain it!

[@pavybez]

Hi professor. Thanks for the wonderful videos. I was wondering why you classify actor critic as model based when the model of the environment is not learnt in this algorithm?

[@imolafodor4667]

thank you for the video, i wonder if there is a value function algorithm which is V(s,t)? Value of state s in time t

[@hassannawazish9300]

Can i find some more detail? or a code with example of bellman equation??

[@RobinCarter]

I strongly recommend the book Reinforcement Learning an Introduction by Sutton and Barto. Also the Winter 2019 online lectures by Stanford (on KZbin). Both have lots of maths and programming exercises.

[@hassannawazish9300]

@@RobinCarter thanks for your reply.

[@Eigensteve]

@@RobinCarter Agreed, these are great resources

[@mariogalindoq]

Let me suggest the book: Grokking Deep Reinforcement Learning by Miguel Morales

[@jeroenritmeester73]

Hi Steve, could you please add the videos to a playlist to avoid accidentally skipping videos?

[@Eigensteve]

Good call -- just added to playlist

[@robinwang6399]

The bellman’s equation reminds me of sequential games from game theory, where you traverse a game tree and optimal choice at each branch leads to globally optimal states.

[@mohammadabdollahzadeh268]

Dear Dr.steve I have a question I think in value iteration we need to use an optimal algorithm;however, in policy iteration we don’t need to use that is it true?

[@cuongnguyenuc1776]

Thanks for the lecture,Are value interation and policy interation learning aslo Temporal Difference learning?

[@rishabsingh6933]

Amazing Content

[@emmanuelameyaw6806]

How many agents can we have in the model?

[@metluplast]

Thanks Professor Steve

[@mohammadabdollahzadeh268]

Dear Dr. Steve I have a question I think according to what you explain to us, in value iteration we need to use an optimal algorithm; however, in policy iteration we don’t need to use that isn’t it Im looking forward to hearing from you Sincerely mohammad

[@lookman_]

thank you, but why does it always have to be so theoratical. Why cant you show an example like the tic tac toe which you mentioned to explain value iteration

[@h2o11h2o]

Thank you

[@parmachine470]

Recursion must be what supply's the reinforcement (feedback) to the value functions and eventually policy. Otherwise we're flying blind.

[@herb.420]

WOOOOOOOOOO THERE IT IS, TIC TAC TOE HAS BEEN SOLVED

[@herb.420]

kzbin.info/www/bejne/rnu1YqKKedlkd80

[@WhenThoughtsConnect]

implicit rolles theorem.

[@schumzy]

Interesting, funny that model based learning isn't highly regarded and so maybe not as explored. I get the feeling that this method will turn out to be as important as the data table function in excel. Quietly, and matter of factly determining a lot of our daily lives. The number of excel simulation models that impact our daily lives, is kinda scary. (think banks, insurance, etc back in the 90's and 2000's. think of all the mergers that were run through an "excel model", all the go/no go business decisions determined by excel models, all based on the data table simulation process, I'm sure model based deep learning has already taken over a lot of that, problem is no one wants to share their business secret sauce, and academia isn't interested in exploring this further. Shame.

[@frankdelahue9761]

I am too dumb to understand this.

[@nononnomonohjghdgdshrsrhsjgd]

wow, you talked 28 minutes and didn't solve any optimization problem with the techniques. I hope you know practically how to apply anything.

[@mohammadabdollahzadeh268]

Dear Dr. Steve I have a question I think according to what you explain to us, in value iteration we need to use an optimal algorithm; however, in policy iteration we don’t need to use that isn’t it Im looking forward to hearing from you Sincerely mohammad