#Reinforcement Learning Course by David Silver# Lecture 1: Introduction to Reinforcement Learning #Slides and more info about the course: goo.gl/vUiyjq
Пікірлер: 327
@jordanburgess8 жыл бұрын
Just finished lecture 10 and I've come back to write a review for anyone starting. *Excellent course*. Well paced, enough examples to provide a good intuition, and taught by someone who's leading the field in applying RL to games. Thank you David and Karolina for sharing these online.
@Gabahulk8 жыл бұрын
I've finished both of them, and I'd say that this one has a better and much more solid content, although the one from udacity is much more light and easy to follow, so it really depends on what you want :)
@adarshmcool8 жыл бұрын
This course is more thorough and for someone who is looking to make a career in Machine Learning, you should put in the work and do this course.
@TheAdithya19918 жыл бұрын
Thanks for the review!
@devonk2987 жыл бұрын
One of the best , if not the best , courses I've watched!
@saltcheese7 жыл бұрын
thanks for the review
@zingg72037 жыл бұрын
<a href="#" class="seekto" data-time="1">0:01</a> Outline Admin <a href="#" class="seekto" data-time="70">1:10</a> About Reinforcement Learning <a href="#" class="seekto" data-time="373">6:13</a> The Reinforcement Learning problem <a href="#" class="seekto" data-time="1320">22:00</a> Inside an RL angent <a href="#" class="seekto" data-time="3420">57:00</a> Problems within Reinforcement Learning
@user-sf5ig4sz6p7 жыл бұрын
Good job. Very thankful :)
@enochsit7 жыл бұрын
thanks
@trdngy82306 жыл бұрын
You made the world much easier! Thanks!
@michaelc24066 жыл бұрын
Problems within Reinforcement Learning 1:15:53
@mairajamil0013 жыл бұрын
Thank you for this.
@Dynamyalo15 күн бұрын
Right now I am sitting in my pajamas in the comfort of my home, eating a peanut butter and jelly sandwich and I have the ability to watch an entire course about an advanced topic online for free. What a time to be alive
@tanmaygangwani35347 жыл бұрын
The complete set of 10 lectures is brilliant. David's an excellent teacher. Highly recommended!
@zhongchuxiong Жыл бұрын
<a href="#" class="seekto" data-time="70">1:10</a> Admin <a href="#" class="seekto" data-time="373">6:13</a> About Reinforcement Learning <a href="#" class="seekto" data-time="382">6:22</a> Sits in the intersection of many fields of science: solving decision making problem in these fields. <a href="#" class="seekto" data-time="550">9:10</a> Branches of machine learning. <a href="#" class="seekto" data-time="577">9:37</a> Characteristics of RL: no correct answer, delayed feedback, sequence matters, agent influences environment. <a href="#" class="seekto" data-time="750">12:30</a> Example of RL <a href="#" class="seekto" data-time="1317">21:57</a> The Reinforcement Learning Problem <a href="#" class="seekto" data-time="1377">22:57</a> Reward <a href="#" class="seekto" data-time="1673">27:53</a> Sequential Decision Making. Action <a href="#" class="seekto" data-time="1776">29:36</a> Agent & Environment. Observation <a href="#" class="seekto" data-time="2032">33:52</a> History & State: stream of actions, observations & rewards. <a href="#" class="seekto" data-time="2233">37:13</a> Environment state <a href="#" class="seekto" data-time="2435">40:35</a> Agent State <a href="#" class="seekto" data-time="2520">42:00</a> Information State (Markov State). Contains all useful information from history. <a href="#" class="seekto" data-time="3073">51:13</a> Fully observable environment <a href="#" class="seekto" data-time="3146">52:26</a> Partially observable environment <a href="#" class="seekto" data-time="3424">57:04</a> Inside an RL Agent <a href="#" class="seekto" data-time="3522">58:42</a> Policy <a href="#" class="seekto" data-time="3591">59:51</a> Value Function: prediction of the expected future reward. <a href="#" class="seekto" data-time="66">1:06</a>:29 Model: transition model, reward model. <a href="#" class="seekto" data-time="68">1:08</a>:02 Maze example to explain these 3 key components. <a href="#" class="seekto" data-time="70">1:10</a>:53 Taxonomy of RL agents based on these 3 key components: policy-based, value-based, actor critic (which combines both policy & values function), model-free, model-based <a href="#" class="seekto" data-time="75">1:15</a>:52 Problems within Reinforcement Learning. <a href="#" class="seekto" data-time="76">1:16</a>:14 Learning vs. Planning. partial known environment vs. fully known environment. <a href="#" class="seekto" data-time="80">1:20</a>:38 Exploration vs. Exploitation. <a href="#" class="seekto" data-time="84">1:24</a>:25 Prediction vs. Control. <a href="#" class="seekto" data-time="86">1:26</a>:42 Course Overview
@eyeofhorus13015 жыл бұрын
Just finished lecture 1 and can already tell this is going to be one of the absolute best courses 👌
@passerby42784 жыл бұрын
what a wonderful time to be alive!! thank god we have the opportunity to study a full module from one of the best unis in the world. taught by one of the leaders of its field
@nguyenduy-sb4ue4 жыл бұрын
how lucky we are to have access to this kind of knowledge only with a button ! Thank you all in DeepMind public this course
@BhuwanBhatta4 жыл бұрын
I was going to say the same. Technology has really made our life easier and better in a lot of ways. But a lot of times we take it for granted.
@sachinkalwar43593 жыл бұрын
@@BhuwanBhatta fvy5tym 🎉4ufgc🙏😎4g🔥f9f4c6v f😎j 9c
@anniekhoekzema93443 жыл бұрын
@@BhuwanBhatta ji kghkfktghjkhhiljcujfjpjkui jikskjgjpj
@socat93115 жыл бұрын
I am a simple man. I see a great course, I press like
@NganVu4 жыл бұрын
<a href="#" class="seekto" data-time="70">1:10</a> Admin <a href="#" class="seekto" data-time="373">6:13</a> About Reinforcement Learning <a href="#" class="seekto" data-time="1317">21:57</a> The Reinforcement Learning Problem <a href="#" class="seekto" data-time="3424">57:04</a> Inside an RL Agent <a href="#" class="seekto" data-time="75">1:15</a>:52 Problems within Reinforcement Learning
@mathavraj96623 жыл бұрын
bless u :)
@tylersnard4 жыл бұрын
I love that David is one of the foremost minds in Reinforcement Learning, but he can explain it in ways that even a novice can understand.
@DEVRAJ-np2ogАй бұрын
hlo, can u please suggeest roadmap for rl.
@Edin12n4 жыл бұрын
That was brilliant. Really helping me to get my head around the subject. Thanks David
@DrTune2 жыл бұрын
Excellent moment around <a href="#" class="seekto" data-time="1450">24:10</a> when David makes it crystal clear that there needs to be a metric to train by (better/worse) and that it's possible - and necessary - to try to come up with a scalar metric that roughly approximates success or failure in a field. When you train something to optimize for a metric, important to be clear up-front what that metric is.
@guupser6 жыл бұрын
Thank you so much for repeating the questions each time.
@tristanlouthrobins6 ай бұрын
This is one of the clearest and most illuminating introductions I've watched on RL and its practical applications. Really looking forward to the following instalments.
@linglingfan81383 жыл бұрын
This is really the best RL course I have seen!
@johntanchongmin3 жыл бұрын
Really love this video series. Watching it for the fifth time:)
@ShalabhBhatnagar-vn4he4 жыл бұрын
Mr. Silver covers in 90 minutes what most books do not in 99 pages. Cheers and thanks!
@user-hb9wc7sx9h11 ай бұрын
David is awesome at explaining a complex topic!. Great lecture. The examples really helped in understanding the concepts..
@Esaens4 жыл бұрын
Superb David - you are one of the giants I am standing on to see a little further - thank you
@alpsahin43405 жыл бұрын
Great lecture, great starting point. Helped me to understand the basics of Reinforcement Learning. Thanks for great content.
@aam18198 ай бұрын
Thank you for sharing your knowledge online. Enjoying your videos, and loving every minute of it.
@asavu Жыл бұрын
David is awesome at explaining a complex topic!
@tianmingdu80227 жыл бұрын
The UCL lecturer is awesome. Thx for the excellent course.
@dhrumilbarot14316 жыл бұрын
Thank you for sharing.It kinda inspires me to always remember that I have to pass it on too.
@sachinramsuran73725 жыл бұрын
Great lecture. The examples really helped in understanding the concepts.
@ethanlyon88247 жыл бұрын
Wow, this is incredible. I'm currently going through Udacity and this lecture series blows their material from GT out of the water. Excellent examples, great explanation of theory, just wow. This actually helped me understand RL. THANK YOU!!!!!
@JousefM4 жыл бұрын
How do you find the RL course from Udacity? Thinking about doing it after the DL Nanodegree.
@pratikd58823 жыл бұрын
@@JousefM I agree, those explanations by GT professors were confusing and less clear, the entire DS nanodegree which had ML, DL and RL was painful to watch and understand.
@nirajabcd3 жыл бұрын
Just completed Coursera's Reinforcement Learning Specialization and this is a nice addition to reinforce the concept I am learning.
@donamincorleone8 жыл бұрын
Great video. Thanks. I really needed something like this :)
@filippomiatto12897 жыл бұрын
Amazing video, a very well-designed and well-delivered lecture! I'm going to enjoy this course, good job! 👍
@sng51928 жыл бұрын
Thanks for a great lecture. I got grasp the point of reinforcement learning !
@wireghost897 Жыл бұрын
It's really nice that he gives examples.
@AndreiMuntean08 жыл бұрын
The lecturer is great!
@lcswillems6 жыл бұрын
A really good introduction course!! Thank you very much!!
@vorushin6 ай бұрын
Thanks a lot for the great lectures! I enjoyed watching every one of them (even #7). This is a great complement to reading Sutton/Barto and the seminal papers in RL. I remember looking at the Atari paper in the late 2013 and having hard time to understand why everyone is going completely crazy about it. A few years later the trend was absolutely clear. Reinforcement Learning is the key to push the performance of AI systems past the threshold where the humans can serve as wise supervisors to the limit when the different kinds of intelligence help each other to improve via self-play.
@zhichaochen77327 жыл бұрын
RL could be the killer app in ML. Nice lectures to bring people up to speed!
@ImtithalSaeed6 жыл бұрын
I can say that I 've found a treasure..really
@vipulsharma38464 жыл бұрын
I am taking a Deep Learning course rn but seriously the comments here are motivating me to get into this one right away.
@hassan-ali-7 жыл бұрын
lecture starts at <a href="#" class="seekto" data-time="390">6:30</a>
@kiuhnmmnhuik26277 жыл бұрын
@<a href="#" class="seekto" data-time="67">1:07</a>:00. Instead of defining P_{ss'}^a and R_s^a, it's better to define p(s',r|s,a), which gives the joint probability of the new state and reward. The latter is the approach followed by the 2nd edition of Sutton&Barto's book.
@mdoIsm771 Жыл бұрын
I took this playlist as a reference for my thesis in "RL for green radio".
@deviljin6217 Жыл бұрын
the legend of all RL courses
@HazemAzim3 жыл бұрын
just amazing and different than any intro to RL
@Abhi-wl5yt2 жыл бұрын
I just finished the course, and the people in this comment section are not exaggerating. This is one of the best courses on Reinforcement learning. Thank you very much DeepMind, for making this free and available to everyone!
@TheAIEpiphany3 жыл бұрын
His name should be David Gold or Platinum I dunno. Best intro to RL on YT, thank you!
@kozzuli7 жыл бұрын
Ty for sharing, Great Lecture!!
@43SunSon5 ай бұрын
Im back again, watching the whole video again.
@MGO20127 жыл бұрын
Excellent explanation. Thank you.
@lauriehartley98084 жыл бұрын
I have never heard a punishment described as a negative reward at any point during my 71 orbits of the Sun. You can indeed learn something new every day.
@mgonetwo Жыл бұрын
Rare opportunity to listen to Christian Bale after he is finished with dealing with criminals as Batman. On a serious note, overall great series of lectures! Thanks, prof. David Silver!
@Newascap3 жыл бұрын
I actually prefer this 2015 class over the most recent 2019 one. Nothing wrong on the other expositor, but David kinda makes the course more smoothly.
@rohitsaka4 жыл бұрын
For Me : David Silver is God ❤️ What a Man ! What an Explanation. One of the Greatest Minds who changed the Dynamics of RL in the past few years.Thanks Deep mind for uploading this Valuable course for free 🤍
@43SunSon4 жыл бұрын
I have to admit, david silver is slightly smarter than me.
@yuwuxiong11654 жыл бұрын
Take swimming as example: learning is part that you directly jump into the water and learn swimming to survive; planning is that part that before jumping into the water, you read books/instructions on how to swim (obviously sometimes planning helps, sometimes not, sometimes counter-helps).
@aaronvr_4 жыл бұрын
really high quality, I'm impressed at David Silver's (or somebody else's?) choice to offer this content to the general public free of charge.. what an age we're living in :DDDDDDDDDDD
@umountable6 жыл бұрын
<a href="#" class="seekto" data-time="2780">46:20</a> this also means that it doesn't matter how you got into this state, it will always mean the same.
@bennog89026 жыл бұрын
awesome course and awesome teacher
@ProfessionalTycoons6 жыл бұрын
amazing introduction and very cool
@VishalKumarTech7 жыл бұрын
Thank you David!!
@rossheaton73835 жыл бұрын
Silver is a boss.
@ABHINAVGANDHI095 жыл бұрын
Thanks for the question at <a href="#" class="seekto" data-time="1188">19:48</a>!
@legorative6 жыл бұрын
Too good :) Best analogies.
@erichuang20094 жыл бұрын
5 days to train per game. now is 5 minutes to complete a train based on recent papers. envolve fast!
@AwesomeLemur3 жыл бұрын
We can't thank you enough!
@merajis6 жыл бұрын
I love this!
@dalcimar5 жыл бұрын
Can you enable the automatic captioning to this content?
@viscaelbarca43812 жыл бұрын
Would be great if you guys could add subtitles!
@abhijeetghodgaonkar6 жыл бұрын
Excellent Indeed!
@iblaliftw2 жыл бұрын
Thank you very much, I recently got a good grade in RL thanks to your great teaching skills!!
@vovos007 жыл бұрын
Thank you for nice lecture
@jamesr1413 жыл бұрын
What a GIFT.
@Delta19G10 ай бұрын
This is my first taste of deep mind
@halefomkahsay29315 жыл бұрын
Great Help Thanks Man
@florentinrieger5306 Жыл бұрын
This is so good!
@vballworldcom5 жыл бұрын
Captions would really help here!
@fandrade93 жыл бұрын
¡Great lecture!
@ajibolashodipo89113 жыл бұрын
Silver is Gold!
@rz44135 жыл бұрын
brilliant course
@yehu79447 жыл бұрын
Could you please turn on the auto generated subscript?
@user-gw5hx9wm9i6 жыл бұрын
Plz..
@Zebra7455 жыл бұрын
As a learner of reinforcement learning, you should become an agent and improve yourself with getting rewards in this environment
@saranggawane47192 жыл бұрын
<a href="#" class="seekto" data-time="2520">42:00</a> - <a href="#" class="seekto" data-time="2875">47:55</a> : Information State/Markov State <a href="#" class="seekto" data-time="3433">57:13</a> RL Agent
@yuxinzhang94033 жыл бұрын
Any observation and reward could be wrapped up into abstract data structure in an object for sorting.
@RahulSharma-yx5uf2 жыл бұрын
Thank you very much!!
@taherhabib31803 жыл бұрын
His 2021 "Reward is Enough" paper makes us agree to the Reward Hypothesis @ <a href="#" class="seekto" data-time="1458">24:18</a> . :D
@AlessandroOrlandi834 жыл бұрын
Amazing teacher I wish I could partecipate to this course! I did a course on Coursera but it was so quick to explain very complex things.
@pratikd58823 жыл бұрын
Are you referring to the RL specialization by Alberta university? If so, then how good was it on the programming/practical aspects?
@AlessandroOrlandi833 жыл бұрын
@@pratikd5882 Yes, I did that. The exercises were good, but I'm not an AI guy but a simple programmer. I managed to do the exercises but I think that explainations were very concise. So in 15 minutes they explain what you get in 1 hour on those lectures. I think that is very summarized. But it's good they have exercises. So I don't think after doing that I'm actually able to do much
@satishrapol36502 жыл бұрын
Do you have any suggestions about which one to start with , the Lecture series here or the RL specialization by Alberta University (on Coursera). I need to apply RL on my own project work. By the way I did the course on Machine learning by NG Andrews and I could follow the pace it was good enough for me and besides the programming exercises helped me alot than I could imagine. But I am not sure if so would be the case with RL by Coursera as well. Can you guide me on this?
@wentingwang883 Жыл бұрын
Thanks so much!
@dharambir_iitk Жыл бұрын
love it!
@prashanthduvvuri78454 жыл бұрын
The future is independent of the past given the present - David Silver
@utsabshrestha2774 жыл бұрын
Only if it have Markov state
@prashanthduvvuri78454 жыл бұрын
The above comment was meant to be in the context of your life. Your brain is a cumulative of all your prior experiences and the choices/decisions which you make will be an a action taken by your brain(which is a markov state). So what I perceived from that statement was that, "you need to forget your past and move on".
@AhmedThabit995 жыл бұрын
if you can activate the subtitle from youtube, it will be great, Thanks
@dashingrahulable7 жыл бұрын
On Slide "History and State" @ <a href="#" class="seekto" data-time="2074">34:34</a>, does the order of Actions, Observations and Rewards matter? If yes, then why the order isn't Observations, Rewards and Actions; the reasoning is that the agent sees the observations first, assesses the reward for actions and then takes a particular action? Please clarify if the chain-of-thought went awry at any place. Thanks.
@ZNE1323Ай бұрын
Goated thanks g
@bingeltube6 жыл бұрын
Recommendable
@vimalrajayyappan2023 Жыл бұрын
Gifted!
@razzlefrog8 жыл бұрын
Only slide that threw me off a bit was the RL taxonomy one. There was some confusion with the redundant labeling, otherwise it was a great lecture!
@donnysoh56105 жыл бұрын
Hi, am the example of the mouse pressing the lever, would that mean that the representation of the agent state will determine how well the agent learns?
@smilylife75153 жыл бұрын
Please add subtitles to make it more helpful for those who are from non English native countries
@shivramshetty55027 жыл бұрын
Hi David, Thank you very much for such great video course. I would be very much appreciated if you help clear the following: 1. Is there a need for training by playing (hundreds of time) say the game as an example before being ready? if you have generalized program designed for reinforcement learning is it ready to play a new game who rules are different or need to be trained again. 2. There is mathematical proof that intermediate rewards can be calculated based on past experience - there is no need to know the intermediate rewards,. It can be derived say using deep mind Q function.- please correct - thank you. 3. In helicopter example current state depends on the past states like velocity acceleration - so not Markov 4. Can the reinforcement learning be realistically used to drive a car or run robot using generalized program that has inputs setup appropriately? Thank you, Sam
@edmonddantes4705 Жыл бұрын
1 Hundreds of times is absolutely nothing in ML or RL. In order to learn to play games with a rich state space like go or chess, AlphaGo or AlphaZero can play billions of games. Also, by "generalised program" you mean architecture or algorithm, like algorithms based on Q-learning, concrete policy gradient methods, etc. If the rules are different, you can use the same algorithm if you reckon it is suitable, but you would have to train from scratch (unless there is a lot of similarity between the games and you can reuse some weights, as one can do with word embeddings in diverse NLP problems). 2 You are not being rigorous about the statement of your question, so it is very hard to understand what you exactly mean. It absolutely necessary to measure intermediate rewards. 3 How is the helicopter state not Markov? The helicopter movement is simulated by running a controlled ODE, and a numerical solver for an ODE is Markov by definition. Of course it is Markov. 4 Self-driving cars are an example of that.
@einemailadressenbesitzerei88163 жыл бұрын
I want to discuss: "All goals can be described by the maximisation of expected cumulative reward" "Do you agree with this statement?" My thoughts why it could be controversy is that you can never specify the reward such as you will never have unexpected side effects/behaviour of the agent. Any other inputs/thoughts?
@aidan98763 жыл бұрын
I found these psychologically useful. Are subtitles available? "The future is independent of the past ,given the present."
@AntrianiStylianou2 жыл бұрын
anyone can confirm if this is still relevant in 2022? I would like to study RL. It seems that there is a more recent series but with a different professor on this channel.
@andyyuan978 жыл бұрын
if subscript provided, then it shoud be perfect and classic~~