Reinforcement Learning Series: Overview of Methods

Поділитися
Вставка
  • Опубліковано 24 лис 2024

КОМЕНТАРІ • 98

  • @EkShunya
    @EkShunya 2 роки тому +15

    I deeply appreciate the quality of knowledge you are providing to the community. please continue to democratise knowledge.

  • @tljstewart
    @tljstewart 2 роки тому +9

    This russian doll of dichotomies has always been a mind bender, often it seems the literature has nebulous definitions and the boundaries aren't so clear. Thank you for the great insights in this lecture, the graphic is superb.

  • @alliwant8383
    @alliwant8383 Рік тому +16

    Superb. One of the things I always I struggle with when learning something is having a well structured map in my head of the topic and subtopics and this does an extremely good job of doing that. Many thanks.

  • @cabbagecat9612
    @cabbagecat9612 Рік тому +3

    Great video! Though imho the on/off-policy distinction explained at 14:24 might be a bit misleading. I believe both on/off policy can explore sub-optimal actions with something like epsilon-greedy.

  • @cornevanzyl5880
    @cornevanzyl5880 2 роки тому

    You helped me during my undergrad, now you're an inspiration to me during my masters.

  • @thrinayreddy3379
    @thrinayreddy3379 2 роки тому +48

    Please make a separate playlist for reinforcement learning :-)

    • @Eigensteve
      @Eigensteve  2 роки тому +25

      Good call -- will do

    • @rudzanimulaudzi7947
      @rudzanimulaudzi7947 2 роки тому +7

      @@Eigensteve please put the videos in order, the current order is not correct. But great content.

  • @akino.3192
    @akino.3192 Рік тому +2

    Wow! Steve, you've managed to break this all down into bite-sized chunks. Thank you 🙏

  • @alireza202
    @alireza202 3 місяці тому +1

    The main difference between on-policy and off-policy methods is the way the generated data is used during learning. If the method uses the data from the current policy, it is on-policy learning. But if the method uses data from another policy (e-greedy or older policies like replays), it is an off-policy method.

  • @complexobjects
    @complexobjects 2 роки тому +8

    I just started getting back into RL so this comes at a perfect time! Looking forward 👌

  • @saitaro
    @saitaro 2 роки тому +10

    OK, this year is gonna be better than I thought. Thanks, professor!

  • @anonymous-tt2lm
    @anonymous-tt2lm 2 роки тому +4

    The heart of AI is reinforcement learning, it is the only most interesting in whole AI/ml. Basically original AI .
    Thanks professor 🤝👍

  • @MrRafaelSencio
    @MrRafaelSencio 2 роки тому +1

    It's been a great series of videos on RL! I'm updating my research interests and now I want to combine MPC with RL in such a way that the resulting control structure can be safely implemented and has some stability guarantees. Thank you very much!

  • @Brian-ft4dh
    @Brian-ft4dh Рік тому +1

    Really really great overview for those new to learning about reinforcement learning! Thanks so much!

  • @MrAndreaCaso
    @MrAndreaCaso 2 роки тому +3

    Finally! Thank you for you posting. Can't wait to see the whole playlist.

  • @eduardolussi104
    @eduardolussi104 Рік тому

    Such a high quality course and a free book in description? You're awesome!!

  • @PippyPappyPatterson
    @PippyPappyPatterson Рік тому +1

    0:00 Intro
    3:00 Background
    7:54 Model & Model-Free Reinforcement Learning (RL)
    8:29 Markov Decision Process (MDP)
    10:25 Nonlinear Dynamics
    13:02 Gradient & Gradient-Free RL
    14:05 Off-Policy (Q Learning) & On-Policy (SARSA) RL
    17:23 Policy Gradient Optimization
    18:05 Deep RL

  • @saeedparsamehr9884
    @saeedparsamehr9884 2 роки тому +2

    I am really grateful for your eye-opening videos, especially this one

  • @GabrielBYPF
    @GabrielBYPF 10 місяців тому

    You really invest perfectly the time in your lessons, very very useful! great series!

  • @jett_royce
    @jett_royce 2 роки тому +2

    Fantastic opening video. You're a talented teacher and I appreciate this content. Looking forward to watching the entire series.

  • @quantum01010101
    @quantum01010101 2 роки тому

    An excellent arrangement of a very tough topic, logical and in the proper flow, keep up the very good job
    Thank you.

  • @Ceznex
    @Ceznex Рік тому

    Coming to this video after a while. Really great video, thank you!!

  • @Mewgu_studio
    @Mewgu_studio Рік тому

    The dichotomy break down are so awesome...

  • @mohammadabdollahzadeh268
    @mohammadabdollahzadeh268 2 роки тому

    Dear steve its amazing category to classify the reinforcement learning thanks alot

  • @rajmeetsingh1625
    @rajmeetsingh1625 2 роки тому +8

    Thanks, Sir, Please add some robotics-related examples in the upcoming series also.

    • @Eigensteve
      @Eigensteve  2 роки тому +4

      Thanks for the suggestion!

  • @ianlorondealmeida9680
    @ianlorondealmeida9680 2 роки тому

    Great didactic, congratulations! I used to confuse myself frequently when dealing with these concepts.

  • @alimustafa2682
    @alimustafa2682 2 роки тому

    I would like to have RL as a career , and you would be the best lecturer for a kickstart.

  • @AlexandreGirard87
    @AlexandreGirard87 2 роки тому +1

    Very nice overview video! There is a small typo in the non-linear dynamic equation, the superflous dt on the right. Regarding how MPC fit in the whole DP framework, I remember Prof. Bertsekas was presenting it as a way to approximate cost-to-go online.

    • @Eigensteve
      @Eigensteve  2 роки тому

      Good catch on the typo! And interesting perspective on MPC -- thanks!

  • @GaetanLepage
    @GaetanLepage 2 роки тому

    Great synthetic and dense video ! Thank you very much for sharing !

  • @XenoZeduX
    @XenoZeduX 2 роки тому +1

    What an amazing start to the new year! 😍

  • @jacekbudzisz380
    @jacekbudzisz380 3 місяці тому

    Great channel. You have a knowledge in the field that I was looking for that is mix on AI/NN and control theory.

  • @apurvdhir7062
    @apurvdhir7062 2 роки тому +6

    Needed this..... Thank you Professor

  • @samirelzein1095
    @samirelzein1095 2 роки тому

    Great teacher and master of the art!

  • @resalatbinafsar7907
    @resalatbinafsar7907 2 роки тому

    Hi Mr. Brunton,
    Your videos are impressive and thank you for making the content. A small suggestion though, it will be better for us to navigate if you make separate playlists with orders in a particular content.

  • @kuanxD
    @kuanxD 2 роки тому

    this explanation is just beautiful! Thx so much

  • @zhehaoli1999
    @zhehaoli1999 2 роки тому

    Great overview, which is just what I need, thank you sir!

  • @MCMelonslice
    @MCMelonslice Рік тому

    This is amazing. Thank you, steve!

  • @mortezaaliyari8818
    @mortezaaliyari8818 2 роки тому +1

    Thanks for the wonderful videos. It would be great if you add real code to the end of the main videos. it would be very easier to understand with detail.

  • @vermashwetank
    @vermashwetank 2 роки тому +1

    Great series! Can you make a contro bootcamp like series for non-linear control theory? Would love to see some simplified explanations for topics like PDE backstepping, reference governors, lyapanov stability criteria etc.

    • @Eigensteve
      @Eigensteve  2 роки тому +2

      Would love to do a bootcamp on this -- maybe a goal for the new year! :)

  • @C7ZR1
    @C7ZR1 7 місяців тому

    Good stuff! You need to remove the "dt" on the right side of your nonlinear dynamics equation.

  • @haotianhang3997
    @haotianhang3997 2 роки тому

    Thank you! Happy New Year!

  • @RasitEvduzen
    @RasitEvduzen 2 роки тому +2

    Thnx for video professor.

  • @drsandeepvm5622
    @drsandeepvm5622 Рік тому

    Great presentation 👏

  • @Spiegeldondi
    @Spiegeldondi 2 роки тому +7

    I am a happy owner of you "Data Driven Science and Engineering" book. That fact that there will be much more content on RL in the 2nd edition is really good news! Will there also be a print version of the 2nd edition of your and Kutz' Book?

    • @Eigensteve
      @Eigensteve  2 роки тому +2

      Thanks! Yes, the print edition should be out sometime later this year.

  • @sinarezaei218
    @sinarezaei218 6 місяців тому

    thanks for your great videos

  • @virgenalosveinte5915
    @virgenalosveinte5915 Рік тому

    Steve, you are amazing.

  • @ShahFahad-hj1ps
    @ShahFahad-hj1ps 2 роки тому +3

    Great job Prof. Steve. How about multi-agent based DRL especially graph learning based RL. That can be a remarkable addition to your playlist.

  • @pedrowangler97
    @pedrowangler97 9 місяців тому +1

    The distinction between On-Policy and Off-Policy explained in this video seems to be different from other sources on the internet. I'm trying to get my head around reinforcement learning and I have noticed that different people have different understandings of certain concepts. Model-free and Model-based are also given a different distinction by others, and this really throws me off. I'm not saying the explanation in this video is incorrect, but that there are different explanations elsewhere and I'm not sure which one is correct.

  • @danish32100
    @danish32100 2 роки тому +2

    Great as always.

  • @WhenThoughtsConnect
    @WhenThoughtsConnect 2 роки тому

    oil lamp except the clear liquid is a gradient and the bubbles are parameters that perform an action. then its p>p' goes to q, then flipflops p q>q'. p'=p or q'=q if the AI improves at a particular task. two randoms cancel each other out on an error function and acts like an implicit rolles theorem without explicitly stating d/dx=0.

  • @thanh315960000
    @thanh315960000 2 роки тому

    Thank you!

  • @marofe
    @marofe 2 роки тому +1

    There is a typo at 10:08, the dynamic model in continuous time should be dx/dt=f(x,u,t) only

  • @bonaldli
    @bonaldli Рік тому +1

    Dear Steve, great explanation. However, just wanna confirm: I thought Actor-Critic is a model-free model?

  • @Janamejaya.Channegowda
    @Janamejaya.Channegowda 2 роки тому

    Thank you for sharing.

  • @paria4393
    @paria4393 Рік тому

    I have Energy data and I need to implement RL on these data (Inverter) to achieve the best result (when charge/discharge battery, when is the best time to feed in grid,etc.) which algorithm should I use for that ?

  • @justlaugh8804
    @justlaugh8804 Рік тому

    Actor critic should be in the policy gradient optimization no?

  • @AksGu2
    @AksGu2 2 роки тому

    Thanks so much for such great video. Can you please tell where does Proximal Policy Optimization (PPO) fit in these categories.
    For my case a small game, I know that I will be using model free RL, but not able to decide what else to use apart from Q-Learning.

  • @Moonz97
    @Moonz97 2 роки тому +2

    At 14:20 to 14:41, you state On-Policy is always playing the best game possible. Is this approach the same as greedily picking the best action at each state? If so, would On-Policy algorithms not include exploration such as epsilon-greedy?
    The way I understood On-Policy vs Off-Policy here is that On-Policy is purely exploitation whereas Off-Policy is both exploration & exploitation. Am I misunderstanding it?
    Thanks!

    • @kunqian6243
      @kunqian6243 2 роки тому +1

      I was also a bit confused at that point. But, I think you have probably misunderstood it since, for RL, we have to always ensure exploration & exploitation. I feel that what I understand is completely the opposite to Prof. Steve's description: on-policy uses the to be improved policy to select an action (meaning not always the best action), while the off-policy uses a different policy to decide which action to take (you may always choose the best action).
      I hope Steve will elaborate more on it. :)

  • @Shaunmcdonogh-shaunsurfing
    @Shaunmcdonogh-shaunsurfing 2 роки тому

    Excellent sunmary

  • @Oliver-cn5xx
    @Oliver-cn5xx Рік тому

    hi steve, I think actor critic are usually considered model-free

  • @hamidmirza333
    @hamidmirza333 11 місяців тому

    What is difference between deterministic policy and stochastic policy?

  • @csalahuni
    @csalahuni 2 роки тому +2

    The link for the new chapter of the 2nd edition of the book is not working for me. Can someone post the correct link in the comments?

    • @AliRashidi97
      @AliRashidi97 2 роки тому

      Yeah it doesnt work :(

    • @Eigensteve
      @Eigensteve  2 роки тому

      Maybe use databookuw.com/databook.pdf

    • @csalahuni
      @csalahuni 2 роки тому +1

      Thank you, this link is working, but it still shows the 1st edition of the book I think.

    • @Eigensteve
      @Eigensteve  2 роки тому +4

      @@csalahuni Shoot, sorry, here is the chapter: faculty.washington.edu/sbrunton/databookRL.pdf added to description too

    • @AliRashidi97
      @AliRashidi97 2 роки тому

      @@Eigensteve tnx professor 🙏

  • @mohammadabdollahzadeh268
    @mohammadabdollahzadeh268 2 роки тому

    Dear professor, please explain to us about how to use reinforcement learning to tune pid gains ❤️
    Im looking forward to hearing from you
    Sincerely mohammad

  • @andreas-lebedev
    @andreas-lebedev 2 роки тому +6

    Why is "Actor Critic" assigned (only) to the left side? Isn't it (also) a combination of gradient free and gradient based algorithms, e.g. the Critic is a DQN and the Actor is a Deep Policy Network?

    • @ayushroy6208
      @ayushroy6208 Рік тому

      I just have one doubt, is A3C a model free one?

    • @mairios521
      @mairios521 5 місяців тому

      I am a beginner in RL field... i think A2C is an actor critic algo as well (and It's a model-free RL)

  • @jadavdas5405
    @jadavdas5405 2 роки тому

    Nice lectures and lots of stuffs to learn. Thanks for sharing. Are the On policy and Off policy somehow related to exploitation and exploration concept?

  • @kundankumar-dt5uu
    @kundankumar-dt5uu Рік тому

    Sir, it model free algorithm uses Marakove decision proce (MDP)?

  • @georgefarnon2432
    @georgefarnon2432 2 роки тому +1

    Excellent. What other topics will be included in the 2nd edition?

    • @Eigensteve
      @Eigensteve  2 роки тому +2

      Updates throughout, all code in Python and Matlab (with R and Julia online), and new chapters on RL and physics informed machine learning

  • @tienphatbui9827
    @tienphatbui9827 7 місяців тому

    At 20:07 Steve said about the "model of system" that if we have a "model of system" we use the model-base, and if we don't have a "model of system" just use model-free. So, can you explain me more about "model of system". What is it? Example? and Why? Thank you so much.

    • @jakal0282
      @jakal0282 Місяць тому

      Model of the system means you know every possible state of the system, every possible next state and the actions that take you there (& with what probability) as well as the rewards earned after every state & action pair. You can have a model of a maze, you CANT have a model of a chess game (unless you make assumptions about the opposing players strategy).

  • @ArmanAli-ww7ml
    @ArmanAli-ww7ml 2 роки тому

    I was reading 1 journal article and found that the author claimed following a model-free RL problem but they have used Markov Decision process to model the problem? they have not mentioned probabilities for states. What does that mean? Also there is another paper which used probabilities for state transitions and solved the problem using Q-learning, so it's all confusing again.

  • @karthiknn97
    @karthiknn97 2 роки тому

    Hello Professor, where will DDPG algorithm sit in this chart?

  • @Matlockization
    @Matlockization 2 роки тому

    I enjoy your broad strokes topics. I was wondering can an AI write to its memory once it learns or discovers something new ? Or it doesn't work like that.

  • @mohammadabdollahzadeh268
    @mohammadabdollahzadeh268 2 роки тому

    Dear steve we can use ls algorithm instead of gradient algorithm isn’t it

  • @ArmanAli-ww7ml
    @ArmanAli-ww7ml 2 роки тому

    Can anyone explain RL by comparing it with ML mathematically? I know much about ML but getting trouble understanding RL.

  • @1812aks
    @1812aks 2 роки тому

    Off plolicy..on policy is slightly confusing here...isnt off policy, a setup where you have the prior data and cant continuously interact with the environment

  • @mohammadabdollahzadeh268
    @mohammadabdollahzadeh268 2 роки тому

    Dear professor please explain to us how to use reinforcement learning to tune pid controller gains
    I’m looking forward to hearing from you
    Sincerely mohammad

  • @alexanderskusnov5119
    @alexanderskusnov5119 2 роки тому

    Will we see the programs teaching each other? (like chess)

  • @nightsailor1
    @nightsailor1 2 роки тому

    Sound level is low.

  • @HarshPatel-g2q
    @HarshPatel-g2q 4 місяці тому

    Actor critic is model based ???? I dont think so.

  • @johnalley8397
    @johnalley8397 2 роки тому

    Bated breath. No, really.
    Hurry uuuuh-uuuup!