Reinforcement Learning 9: Model-based methods
45:46
Reinforcement Learning 9: Model-based methods
3 жыл бұрын
Reinforcement Learning 10: Extended methods
52:59
Reinforcement Learning 10: Extended methods
3 жыл бұрын
Reinforcement Learning 8: Policy gradient methods
49:43
Reinforcement Learning 8: Policy gradient methods
3 жыл бұрын
Reinforcement Learning 6: Temporal-difference methods
41:21
Reinforcement Learning 6: Temporal-difference methods
3 жыл бұрын
Reinforcement Learning 4: Dynamic programming
44:45
Reinforcement Learning 4: Dynamic programming
3 жыл бұрын
Reinforcement Learning 7: Function approximation
49:40
Reinforcement Learning 7: Function approximation
3 жыл бұрын
Reinforcement Learning 5: Monte Carlo methods
41:06
Reinforcement Learning 5: Monte Carlo methods
3 жыл бұрын
Reinforcement Learning 3: OpenAI gym
1:23:17
Reinforcement Learning 3: OpenAI gym
3 жыл бұрын
Reinforcement Learning 2: Markov Decision Processes
54:04
Reinforcement Learning 2: Markov Decision Processes
3 жыл бұрын
Reinforcement Learning 1: Foundations
51:34
Reinforcement Learning 1: Foundations
3 жыл бұрын
Deep Learning 10: Meta learning and manifold learning
1:01:41
Deep Learning 10: Meta learning and manifold learning
3 жыл бұрын
Deep Learning 9: Flow models and implicit networks
52:51
Deep Learning 9: Flow models and implicit networks
3 жыл бұрын
Deep Learning 7: Energy-based models
53:24
Deep Learning 7: Energy-based models
3 жыл бұрын
Deep Learning 3: PyTorch programming (coding session)
1:01:57
Deep Learning 3: PyTorch programming (coding session)
3 жыл бұрын
Deep Learning 8: Sequential models
53:39
Deep Learning 8: Sequential models
3 жыл бұрын
Deep Learning 6: Adversarial models
48:30
Deep Learning 6: Adversarial models
3 жыл бұрын
Deep Learning 5: Generative models
47:21
Deep Learning 5: Generative models
3 жыл бұрын
Deep Learning 4: Designing Models to Generalise
55:50
Deep Learning 4: Designing Models to Generalise
3 жыл бұрын
Deep Learning 1: Introduction
57:12
Deep Learning 1: Introduction
3 жыл бұрын
Gradient Origin Networks (GONs)
2:45
Gradient Origin Networks (GONs)
4 жыл бұрын
Interactive GPU active contours for segmenting inhomogeneous objects
4:41
Interactive GPU active contours for segmenting inhomogeneous objects
6 жыл бұрын
ABI: Automatic 3D Billboard Imposters
2:58
ABI: Automatic 3D Billboard Imposters
11 жыл бұрын
Starship Physics
3:48
Starship Physics
11 жыл бұрын
Пікірлер
@mk_upo
@mk_upo 6 ай бұрын
Great! Thanks
@BlueBirdgg
@BlueBirdgg 7 ай бұрын
Interesting example on 14:00. Watched your 2 series. Ty very much!
@monkeysareaproblem1743
@monkeysareaproblem1743 7 ай бұрын
looks like the colab code is outdated step # setup the environment, and record a video every 50 episodes gives: AttributeError: module 'gym.wrappers' has no attribute 'Monitor' also a lot of deprecation warnings
@BlueBirdgg
@BlueBirdgg 8 ай бұрын
Thank you for the classes! Incredible so far!
@ichaa3tech
@ichaa3tech 10 ай бұрын
This is seriously very underrated, the best
@bello3137
@bello3137 10 ай бұрын
You extract just the key things needed in sutton's book. I follow his book while following your videos and bunch others as well 😁 thank you
@SaschaRobitzki
@SaschaRobitzki 11 ай бұрын
Why is the action q* going from class3 to the pub 9.4?
@fatemehnorouzi1722
@fatemehnorouzi1722 11 ай бұрын
I have watched several lectures about RL and you have been the best one
@bello3137
@bello3137 10 ай бұрын
same here.
@ichaa3tech
@ichaa3tech 10 ай бұрын
saaame
@mohammadnadeem839
@mohammadnadeem839 Жыл бұрын
i am the 2k th person added in your subscriber list
@lovol2
@lovol2 Жыл бұрын
Thanks. Was good to hear there is lack of consistency in the notation used in papers as that was confusing!
@wajidiqbal5633
@wajidiqbal5633 Жыл бұрын
thank you prof, for this elegant explanation....
@compsciorbust9562
@compsciorbust9562 Жыл бұрын
Incomplete list of timestamps: 0:00 - Introduction 3:01 - Installing Conda 13:25 - Using Torch (tensors) 23:00 - Using Torch (data parsing) 32:15 - Using backprop 52:00 (ish) - Using convolution
@ARREYAR
@ARREYAR Жыл бұрын
The best lectures on RL
@hayaquraan-p3o
@hayaquraan-p3o Жыл бұрын
it was perfect thank you so much
@xiaocenliu
@xiaocenliu Жыл бұрын
thank you so much for not assuming students knowing everything 😭. You explain it so clear!
@jrohit1110
@jrohit1110 Жыл бұрын
Chapter 12 Sutton and Barto. This is what I was looking for. Thanks for beautiful the explanation!
@AymenSekhri-gw8wh
@AymenSekhri-gw8wh Жыл бұрын
Thank you so much ! rich content for free.
@AymenSekhri-gw8wh
@AymenSekhri-gw8wh Жыл бұрын
Good Explanation, thank you so much
@yuktikaura
@yuktikaura Жыл бұрын
Possible for you to share the latex template for the presentation?
@ichaa3tech
@ichaa3tech 9 ай бұрын
riight
@chanpreetsingh007
@chanpreetsingh007 Жыл бұрын
thanx
@yuktikaura
@yuktikaura Жыл бұрын
How do we conclude that ->success: {stats/episode} would always be monotonically increasing? And how does it indicate convergence with value as 0.54?
@cwkx
@cwkx Жыл бұрын
Hi I can't remember what I said here, it was over 2 years ago - we go into depth on the convergence properties for this in our practicals, which are on my github: github.com/cwkx/materials/raw/main/reinforcement-learning/rl-answers4.pdf and github.com/cwkx/materials/blob/main/reinforcement-learning/rl-answers5.pdf etc
@yuktikaura
@yuktikaura Жыл бұрын
Thanks for a well explained topic.
@yuktikaura
@yuktikaura Жыл бұрын
Thank you for doing these videos... I found them really very helpful
@hom01
@hom01 Жыл бұрын
Amazing lecture, thanks for uploading
@maryamfarajzadeh2262
@maryamfarajzadeh2262 Жыл бұрын
I really recommend this video! Just perfect! I wish POMDP was also well explained in the same way!
@GeneralKenobi69420
@GeneralKenobi69420 Жыл бұрын
sassy 💅
@danielji5184
@danielji5184 2 жыл бұрын
good lecture
@agustinrovira2955
@agustinrovira2955 2 жыл бұрын
Great job !
@benmiss1767
@benmiss1767 2 жыл бұрын
Very very useful and informative thank you very much!
@rladndud1722
@rladndud1722 2 жыл бұрын
35:02 implicit networks
@alebadi
@alebadi 2 жыл бұрын
You started not knowing what you are talking about.
@phenixzhang4224
@phenixzhang4224 2 жыл бұрын
As a newcomer who has already learned pytoch, this class has allowed me to consolidate the actual combat practice of torch and understand the magic of vision. In addition, I would like to ask Willcocksr: How should we learn more about using pytoch to build our own network?
@aliheidary355
@aliheidary355 2 жыл бұрын
could you speak louder in your next video
@BlissfulBasilisk
@BlissfulBasilisk 2 жыл бұрын
On Langevin Dynamics in Machine Learning - Michael I. Jordan (Video Link): kzbin.info/www/bejne/h4XRm6Saraxsb8U&ab_channel=InstituteforAdvancedStudy
@bing6740
@bing6740 2 жыл бұрын
The example of car accident got me
@malathreayad
@malathreayad 2 жыл бұрын
Excellent explanation, well done
@AhamedKabeer-wn1jb
@AhamedKabeer-wn1jb 2 жыл бұрын
Thank you..
@엄의섭
@엄의섭 2 жыл бұрын
By far one of the most thorough and helpful explanations I've encountered! THANKS!
@shahardagan1584
@shahardagan1584 2 жыл бұрын
Hi great lectures! i would like to know if you can recommend me more courses and resources to advance in the field
@cwkx
@cwkx 2 жыл бұрын
I'd just recommend just getting into a habit of reading the latest papers from the top venues such as ICLR, NeurIPS and CVPR when they've been reviewed, e.g. find a sorted ranked list of the best papers and read the abstracts and Ctrl+F any terms interesting to you - e.g. tanelp.github.io/neurips2021/ and papers.labml.ai/papers/iclr_2022?sort_by=conference_score&dsc=0
@Manishkumar-ww4gm
@Manishkumar-ww4gm 3 жыл бұрын
Very nice explanation sir.Thank you
@amirmahdikhosrvitabrizi7516
@amirmahdikhosrvitabrizi7516 3 жыл бұрын
It was amazing, this lecture has made my life much easier. thank you.
@Jannls
@Jannls 3 жыл бұрын
Your video helped me a lot! Very informative and easy to understand. Thank you!
@joaoborges2014
@joaoborges2014 3 жыл бұрын
Amazing lecture, thank you so much!
@saharrahimimalakshan5485
@saharrahimimalakshan5485 3 жыл бұрын
It was an amazing video, you explained the issues in the best way. Thank you
@phenixzhang4224
@phenixzhang4224 3 жыл бұрын
Recently I followed the teacher’s second class on and off, involving some basic theoretical knowledge related to backpropagation. The main difficulty is still in the formula described in English, but I can feel the improvement of listening. I also manually offline deduced the back-propagation algorithm and implemented it in python, keep going!
@AECTechJourneys
@AECTechJourneys 3 жыл бұрын
This is gem. Great content.
@johnnassour
@johnnassour 3 жыл бұрын
Would you please check the calculation for 0.34? It is 0.3125 in my calculation. Thank you.
@cwkx
@cwkx 3 жыл бұрын
0.34375 = 0.25*0.0625 (left) + 0.25*0.0625 (up) + 0.25*0.25 (down) + 0.25*1 (right) - you can see this clearly if you go to the colab notebook in the comment, then in the Policy evaluation section, where it first says "# evaluate this policy ... V = policy_evaluation(env,policy,draw=False)" change draw=True and you'll see all the intermediate steps and you can see 0.34375.
@johnnassour
@johnnassour 3 жыл бұрын
@@cwkx so you use the updated valves in the same episode. I thought they will be used in the next episode.
@harrivayrynen
@harrivayrynen Жыл бұрын
@@johnnassour Yes there must be mistake in video's calculations. If you look algorithm, the array is updated when all states are gone through. But still very good video series, thanks for that.
@phenixzhang4224
@phenixzhang4224 3 жыл бұрын
Deep learning is indeed developing faster and faster, which requires us to understand it in essence, including biological perspectives, historical perspectives, etc. I hope I can build a more systematic understanding of deep learning through this course. By the way, Teacher Willcocks's English expression is very fluent, and it doesn't sound particularly strenuous.
@Dian87barry
@Dian87barry 3 жыл бұрын
Hello Dear Sir Interesting Video, Please did it possible to have the code for this video
@cwkx
@cwkx 3 жыл бұрын
Hi Mamadou, all code where available are in the video descriptions (Colab links).
@Dian87barry
@Dian87barry 3 жыл бұрын
@@cwkx thank you
@alialtan8182
@alialtan8182 3 жыл бұрын
Hi there,big fan! I learned that you also had expertise in security, is there any chance you will consider teaching them in youtube ?
@cwkx
@cwkx 3 жыл бұрын
Hi Ali, many thanks for the kind comment - unfortunately I don't think I can get permission for this due to the sensitive nature of some of the security materials/discussions/exploits/real-world stories not covered in the slides.