DeepLearning.TV
Reinforcement Learning has started to receive a lot of attention in the fields of Machine Learning and Data science. In January of 2016, a team of researchers from Google built an AI that beat the reigning world champion of the board game Go. This AI, AlphaGo, utilizes reinforcement learning in order to discover new strategies. Despite the potential of reinforcement learning, there are very few learning resources currently available. This video will help to demystify the field so that its capabilities can be better understood.
Deep Learning TV on
Facebook: https://www.facebook.com/DeepLearningTV/
Twitter: https://twitter.com/deeplearningtv
Relevant URLs
Richard Sutton book: https://webdocs.cs.ualberta.ca/~sutton/book/ebook/the-book.html
Tambet Matiisen post: https://www.nervanasys.com/demystifying-deep-reinforcement-learning/
Andrej Karpathy post: http://karpathy.github.io/2016/05/31/rl/
Credits
Nickey Pickorita (YouTube art) –
https://www.upwork.com/freelancers/~0147b8991909b20fca
Isabel Descutner (Voice) –
https://www.youtube.com/user/IsabelDescutner
Dan Partynski (Copy Editing) –
https://www.linkedin.com/in/danielpartynski
Marek Scibior (Prezi creator, Illustrator) –
http://brawuroweprezentacje.pl/
Jagannath Rajagopal (Creator, Producer and Director) –
https://ca.linkedin.com/in/jagannathrajagopal
Source
Fun topic to learn and skill to have – enjoy 🙂
How does it actually choose which action to take though? Does it just make a tree of all possible actions and the predicted reward up to a certain depth and then choose the action with the highest reward (similar to minimax)? That seems like it would be very computationally expensive.
I'm still a bit confused how exactly the Atari's screenshots helped the net to make decisions… And also, it was said that it was not a classification problem, but rather a regression problem. Was this topic already covered in any video? Thanks for the videos, I've watched all of them from the very beginning 🙂
And how does this look like in actual code?
thank you:)
Do you have something about extrreme learning?
Are there gonna be more videos? What happened? I really enjoyed this series!
who will give the reward? where is the score come from?
Please make more videos, I;m not sure as to why your videos have stopped completely
Hi, I am a Machine Learning student. I found your videos here explain the concepts and problems very clear. Unfortunately, Youtube is blocked in China. Can I ask you to grant me translate and redistribute your videos in China? Thank you!
we are using deep learning in our project. like intelligent gas sensor. i need a advice which net to choose or which software to use
why you stop making videos?
why you stop making videos???
Great Video!!
I've created a simple implementation of Reinforcement Learning (Deep Learning ) to train a model to play the game tic tac toe (3×3). it kinda plays with itself learns from the outcome and gets better, I've used tensor flow for this.
you can find the code at github link given below:
https://github.com/jamesq9/Tic-Tac-Toe-Machine-Learning-Using-Reinforcement-Learning
the last video
Not clearly explained. I haven't understood that is reinforced learning.
Finished watching the series/playlist. Thank you. Your explanation, enunciation, and choice of images/visuals is on point. Keep up the good work. I learnt more from your videos than from my class albeit at a higher level. I hope you'll be rewarded with good ad revenue.
If possible, please cover other important concepts like SVM, Naive Bayes, probabilistic graphic models etc.. or maybe new series called Machine Learning simplified?
So good
I am in the beginning of writing my thesis which focuses on deep learning, i and i just finished watching all your videos and they were exactly what i wanted. I just wanna say thanks, you really helped guys!
So easy and fun all vids on this channel.
Im just sad it's been 2 years this channel uploaded.
Get back to me!!!