An introduction to Reinforcement Learning

This episode gives a general introduction into the field of Reinforcement Learning:
- High level description of the field
- Policy gradients
- Biggest challenges (sparse rewards, reward shaping, ...)
This video forms the basis for a series on RL where I will dive much deeper into technical details of state-of-the-art methods for RL.
Links:
- "Pong from Pixels - Karpathy": karpathy.github.io/2016/05/31/rl/
- Concept networks for grasp & stack (Paper with heavy reward shaping): arxiv.org/abs/1709.06977
If you enjoy my videos, all support is super welcome!
/ arxivinsights
If you have questions you would like to discuss with me personally, you can book a 1-on-1 video call through Pensight: pensight.com/x/xander-steenbr...
::Chapters::
00:00 Intro
01:03 So what is Reinforcement Learning?
03:39 Learning without explicit examples
07:25 Main challenges when doing RL
15:04 Are the robots taking over now?

[@rednassie1101]

People: ANN ARE TAKING OVER THE WORLD AND STUFF WILL NEVER BE THE SAME my horribly trained network on a cat: "dog"

[@I_Lemaire]

Could they help with the necessary government takeovers associated with COVID-19? Temporary command economies could be more efficient.

[@revimfadli4666]

KZbin's bots: "Robot fighting is animal cruelty"

[@SukhwinderSingh-fb9qw]

This was one of the best videos on RL that I have seen. Extremely informative. The way you explain things is awesome. Keep up the great work! Cheers man!

[@yuanyuansun3521]

“If u only give it a positive reward when it successfully stacked a block, it’ll never get to see any of those reward” Only if my tutors realise this.

[@DanielHernandez-rn6rp]

Love this guy. As an RL PhD student, your videos are golden.

[@nikhillondhe5815]

RL PhD sounds so interesting!

[@andres18m]

Institute name?

[@Ayanwesha]

hello..sir i am a grad stud can anyone tell me plzz if back propagation is necessary in supervised and unsupervised learning?or it is only used in reinforcement learning thanks

[@hcgaron]

Ayanwesha 12345 yes, back propagation is used as a basis for gradient based methods of optimization

[@ernie2111]

"RL PhD" didn't know such things exist lol

[@floriandebrauwer9140]

Thanks for your work ! I like the way you present such a complex field in a clear manner for poeple without any background. Thanks to you I know where to start in my learning journey !

[@shashankshivakumar4732]

I love this video. I love his criticial and grounded thinking. Great work !

[@jackwhite9332]

Impressive explanation, found this very useful. Thank you!

[@denebvegaaltair1146]

Your videos have just the right amount of technical terms such that student engineers can learn something, and also the right amount of summary and rewording such that beginners can get a vague idea of concepts. Thank you so much

[@MuditBachhawatIn]

I have been meaning to read about RL for a long time. This video couldn't be more simple and clear introduction to it. Thanks man!

[@josefpolasek6666]

Your videos are absolutely amazing! Thank you very much for explaining concept of RL in 16 minutes.

[@7810]

Good stuff to learn the RL in terms of basic knowledge as well as the challenge it will face. Thanks for your time and sharing!

[@nemx4u]

You explain hard topics beautifully! great job. Would love to see more RL videos!

[@orfeasliossatos]

I've been literally looking all over for a video like this, thank you so much

[@gusbakker]

Great balance between a very well explained content and the interesting facts about current progress in AI at the end. Good work

[@cemgocer8185]

Quality of the video is off the charts. Topics u have chosen to explain the field, the way u explain them and especially pointing the common misconceptions that make it harder for us to get into what AI really is... I'm sad that there is no superlike button. Rare to see videos of this quality and honesty

[@Hyuts]

Explains in an elegant manner more than I have learned in half a semester of my AI college course.

[@angelakong653]

This was really helpful. Thank you to people like you for creating this content. Appreciate you, Xander!

[@Krimson5pride]

It was both professional and entertaining at the same time. Great and precise explanation.

[@snippletrap]

The perils of reward shaping are well understood in a public policy context, where incentives can lead to "unintended consequences".

[@josephedappully1482]

This is a great video; thanks for making it! Looking forward to your next one.

[@TY-un4no]

Complex stuff made simple and easy, this is a very good intro video to RL. Starting to learn RL for work and your video gave me a great starting point, thank you!

[@codyheiner3636]

Love the philosophical discussion at the end!

[@mohammadhatoum]

Great job.. Explained the subject in a simple way. Keep it up and looking forward for new videos

[@lincolnaisagbonhi8953]

This is a great presentation on RL, short and clear content.

[@saaniausaf9621]

I loved the way you explained everything. Thanks!

[@Jshizzle2]

Perfect video, so much more intuitive than my lectures. Thanks a bunch!

[@PriyanshuGupta-hf2hm]

You explained so well that I understood each and everything in your video. I am overjoyed!

[@jonathaskerber5472]

Such a great introduction. Keep up the good work!

[@matfuckk4736]

Great quality and well-appreciated content. Please, continue, became your patron.

[@Lilowillow42]

Just wanted you to know that in my university course for introduction to AI our professor recommended your videos for machine learning. Your explanation is highly enjoyable and informative. Thank you!

[@nateshrager512]

Great job introducing the topic. Very nice job dispelling misconceptions surrounding the topic as well. I put on that notification for your next videos, looking forward to em : )

[@sharadrawatindia]

Hey Xander! Great videos. Looking forwards for your next video.

[@dean8147]

You’re a legend mate. Honestly, thanks for all of your hard work

[@ArnauViaMartinezSeara]

Really useful. I am preparing a Reinforcement Learning class aplied to finance and it is really helpful. Can't wait to see next episode. Thanks

[@davidfield5295]

The misuse of 'literally' notwithstanding, this was an excellent video. Very clear and concise explanation.

[@luiseduardocorralesmendoza9396]

Great examples and great explanation, thank you i was struggling with this topic

[@Alex-gc2vo]

your videos are some of the best explanations I've found for a lot of these very advanced subjects. I suspect your viewer count is going to jump very quickly. keep it up.

[@OliverZeigermann]

Very lively and understandable. Great work!

[@tonakkie635]

Great overview, well explained👍.Thanks

[@soumyakantadash5986]

These videos are gem!!!..... incredible, precise and knowledgeable!!!!

[@tnmygrwl]

You do an awesome of structuring the content. Loved the video.

[@mehdisauvage1234]

Your videos are so useful and interesting ! This is pure gold to me :)

[@RoxanaNoe]

Your channel is a great resource for getting into Deep Learning and AI.

[@mantische]

One of the best explanations I've seen

[@alirezaparsay8518]

The explanation was so clear. Thank you.

[@empiricistsacademy7181]

Thanks youuu for this video. Looking forward to your future videos!

[@amitredkar140]

Great video!!!! Explained exceptionally, liked other videos as well from your channel. Would love to see more stuff related to AI/DL or RL. Thanks in advance. Keep up the good work....

[@Z4NT0]

I learned so much in just 16 minutes. Awesome Video!

[@bjbodner3097]

Great video, great channel! Thanks so much for making this! Can't wait to watch more:)

[@majeedhussain3276]

You deserve million subscribers hopefully one day you will. So much clarity in every video. Keep going...

[@ArturoMoraSoto]

Nice explanation, thanks for taking the time to create this great video.

[@jorgegarcia-torresfdez2471]

You did again a really nice work ! Congratulations :D

[@payam-bagheri]

Brilliant video!

[@TheBeansChopper]

I think the comment section speaks for itself. This is a fantastic grasp of the basic concepts and issues with this technologies in such short time, without diving unnecessarily into formalism. Thanks :)

[@thanasispappas62]

By far the best video of RL ive ever seen.

[@senri-]

Cant wait for the next videos keep up the great work!

[@atcer51]

fiiiinnnaaaallly after tons of googling, I finally fund a USEFUL video that accually EXPLAINS how to reward the agent, and not just saying: 'oh u just reward it'

[@adammenges6300]

your videos are so good, keep up the great work 💪🏻

[@maisamwasti]

Your videos = super informative! Thanks a lot for the good work

[@khajasaen]

Best channel in the crowd ... keep it up Xander

[@allamasadi7970]

Your channel deserves more views 👍

[@akramsystems]

agree %100

[@lohithArcot]

Not many reach these topics.

[@aanex2005]

I have no idea about RL but your video has given me a good jump start. Thanks man

[@sidharthaparhi7930]

Also your intro is very high quality, like an intro to a good TV show

[@thaermashkoor6225]

Thanks for this clear introduction.

[@rishidixit7939]

The sudden surprise of hearing Bruno Mars makes you pause video for other open tabs

[@poojanpatel2437]

Best Channel on yt for ml/dl/rl/ai... Keep up the good work... Would love to see your new video weekly...

[@ArxivInsights]

I'd love to make more videos too! But since I'm currently doing this 100% in my spare time and 1 vid takes about 30hrs of work, there's really no way I can do one per week for now :(

[@poojanpatel2437]

Arxiv Insights Still amazing work till now... Love to see your more videos in future.. ❤

[@alenasazanova8331]

That's very interesting and understantable video. Thank you very much!

[@skviknesh]

Awesome!!!!!! Bro!!! Great explanation! !!!! Keep continuing!!!

[@011azr]

Your explanations are great, thanks :)

[@ms_1918]

well came here for a 1 min intro to reinforcement learning for first class of course, stopped after 16 minutes what a superb experience.

[@andreasnatsis3027]

Amazing video. Keep up the good work and soon your channel will explode!

[@alanator25]

Thank you! This was a great introduction!

[@erosennin950]

looking forward to the next one, awsomee

[@mgilson]

I can't wait for your next video !! 😍😍😍

[@shahulhameed-xc1to]

Great learning experience. Thank you

[@wzyjoseph7317]

Very clear explaination! Thanks for the work!!!!XD

[@christopherwolff8443]

These videos are great. Keep it up!

[@ingeniouswild]

Very nice episode! One thing that struck me about your suggestion that without Reward Shaping, the auto-learning of the 2600 games would be intractable: even for a human, this would be extremely difficult - we succeed with new, undocumented games because they often have similar sub-components and sub-goals that we already know from other games (or life). But I'm sure you could easily construct a game which would be impossible for a human to learn without any hints, while still having the same overall complexity.

[@elvispiss]

Even after doing my second course of RL, this video is still so informative in its simplicity. Great videos

[@abedinization]

Thank you, very informative video!

[@karFLY1]

Great as usual. Thank you :)

[@keshavlakhotia1432]

I will also love to see u Again in next episode

[@ipuhbamrash6708]

Fabulous!! No other word for you!!

[@rajendrarao3057]

awesome video sir. please keep up the good work in this field....

[@digvijaybhandari9747]

Really enjoyed the content here!

[@qandos-nour]

Great and clear explanation

[@gudusangtani]

So well explained ....I also liked the comments on Boston robotics considering the hype and buzz about AI and ML.. You are doing a very good job !

[@sridhasridharan3600]

Great Videos! I am recommending these to my students.

[@stefano3808]

really high quality videos, thanks for that

[@merrilalmeida5982]

thanks so much Arxiv.

[@gorillapimpin2978]

my new favorite channel

[@azmathmoosa4324]

I like how u don't hype up anything. Great mate! I subscribe!

[@Vladeeer]

Awesome video, keep up the good work!

[@laeeqahmed1980]

Great talk. Humans are not good at multiple sound recognition and you added music to your video.

[@owencarey3216]

Amazing video! Thank you so much.

[@neerajkulkarni]

Wow, great stuff! Subscribed.

[@amydeng1883]

Thank you so much for your videos!

[@Red-ft9sb]

Well explained! Kudos!

[@biiigates7381]

I've been learning AI for almost a year now and on all the channels I've spent with this is the best one. Very underrated! (btw its the first time i discovered this channel and I instantly subscribed)

[@mundeepcool]

Same here, loved this video and I instantly subscribed... and also oh yeah yeah

[@SageElliott]

What a fantastic channel!! 😊