DQN explained line-by-line.
Deep Q Networks (DQN) form the cornerstone of progress in Deep Reinforcement Learning, thus making it important to get a grasp on the working of the algorithm. In this video we will work our way through the 2015 Nature paper titled 'Human-level control through deep reinforcement learning'. This video will help break down the algorithm in a manner that is easy to implement. We decompose the algorithm into three classes, namely ReplayMemory, DQNNet and DQNAgent, each of which we inspect individually.
---------------
Hey there, you wonderful being! 👋
Hope you are all doing well. Thanks for stopping by, I hope you found the video useful. ✨
---------------
// Resources related to this topic that you might find interesting: 📑
1. Human-level control through deep reinforcement learning (the 2015 Nature paper): https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf
2. Playing Atari with Deep Reinforcement Learning (the 2013 vanilla-DQN paper): https://arxiv.org/pdf/1312.5602.pdf
3. My series of posts on DQN: https://www.saashanair.com/dqn-theory/
4. My repo on GitHub associated with the posts: https://github.com/saashanair/rl-series/tree/master/dqn
5. Intuitive introduction to DQN: https://youtu.be/qtxF33tFKJc
6. Blogpost that complements this video: https://www.saashanair.com/dqn-code/
// Timestamps ⌛️
0:00 Intro and modular design
0:50 Replay Memory: Add and use experiences, Benefits
2:53 DQNNet: Online, Target and Architecture
3:55 DQNAgent: How to act, exploration vs exploitation, Epsilon-greedy
5:50 DQNAgent: How to learn, Q-value recap, updating the online and target networks
7:47 Walk through of the algorithm presented in the paper
9:16 See ya 👋
// Who am I? 👩💻
I respond to the names: Saasha, Sash and Nair. Unless of course, I am lost in my own world, which, I must warn you, happens quite often. 🤪
I am interested in all things AI, especially topics relating to Reinforcement Learning and Safety. I am currently located in Pisa, Italy where I am pursuing a year long research fellowship at the Sant'Anna School of Advanced Studies. My work focuses on improving trustworthiness and robustness of the ML-based components in Autonomous Vehicles. 🚗
// Why this YouTube channel? 🎥
First of all, good on you for taking your learning in your own hands. I am proud of you for wanting to expand your limits. But self-learning can be quite a lonely journey. So, if you are interested, let's claim this little slice of the internet as our own and build a community where our quirky nerdy selves can shine. Let's support one and other as we follow our curiosities and explore the vast and expansive world of AI. 💙
// Let's connect 📮
Website: https://www.saashanair.com
LinkedIn: https://www.linkedin.com/in/saashanair/
Twitter: https://twitter.com/nair_saasha
Mail: saasha.allthingsai@gmail.com
---------------
Subscriber count: 96
Видео DQN explained line-by-line. канала Saasha Nair
---------------
Hey there, you wonderful being! 👋
Hope you are all doing well. Thanks for stopping by, I hope you found the video useful. ✨
---------------
// Resources related to this topic that you might find interesting: 📑
1. Human-level control through deep reinforcement learning (the 2015 Nature paper): https://storage.googleapis.com/deepmind-media/dqn/DQNNaturePaper.pdf
2. Playing Atari with Deep Reinforcement Learning (the 2013 vanilla-DQN paper): https://arxiv.org/pdf/1312.5602.pdf
3. My series of posts on DQN: https://www.saashanair.com/dqn-theory/
4. My repo on GitHub associated with the posts: https://github.com/saashanair/rl-series/tree/master/dqn
5. Intuitive introduction to DQN: https://youtu.be/qtxF33tFKJc
6. Blogpost that complements this video: https://www.saashanair.com/dqn-code/
// Timestamps ⌛️
0:00 Intro and modular design
0:50 Replay Memory: Add and use experiences, Benefits
2:53 DQNNet: Online, Target and Architecture
3:55 DQNAgent: How to act, exploration vs exploitation, Epsilon-greedy
5:50 DQNAgent: How to learn, Q-value recap, updating the online and target networks
7:47 Walk through of the algorithm presented in the paper
9:16 See ya 👋
// Who am I? 👩💻
I respond to the names: Saasha, Sash and Nair. Unless of course, I am lost in my own world, which, I must warn you, happens quite often. 🤪
I am interested in all things AI, especially topics relating to Reinforcement Learning and Safety. I am currently located in Pisa, Italy where I am pursuing a year long research fellowship at the Sant'Anna School of Advanced Studies. My work focuses on improving trustworthiness and robustness of the ML-based components in Autonomous Vehicles. 🚗
// Why this YouTube channel? 🎥
First of all, good on you for taking your learning in your own hands. I am proud of you for wanting to expand your limits. But self-learning can be quite a lonely journey. So, if you are interested, let's claim this little slice of the internet as our own and build a community where our quirky nerdy selves can shine. Let's support one and other as we follow our curiosities and explore the vast and expansive world of AI. 💙
// Let's connect 📮
Website: https://www.saashanair.com
LinkedIn: https://www.linkedin.com/in/saashanair/
Twitter: https://twitter.com/nair_saasha
Mail: saasha.allthingsai@gmail.com
---------------
Subscriber count: 96
Видео DQN explained line-by-line. канала Saasha Nair
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Intuition of the DQN algorithm](https://i.ytimg.com/vi/qtxF33tFKJc/default.jpg)
![Everything you need to get started using OpenAI Gym to train RL agents.](https://i.ytimg.com/vi/cxMuWd83fI8/default.jpg)
![Coding Deep Q-Learning in PyTorch - Reinforcement Learning DQN Code Rainbow Tutorial Series p.1](https://i.ytimg.com/vi/NP8pXZdU-5U/default.jpg)
![The what, why and how of Reinforcement Learning.](https://i.ytimg.com/vi/I_zlzO250EA/default.jpg)
![An introduction to Reinforcement Learning](https://i.ytimg.com/vi/JgvyzIkgxF0/default.jpg)
![What makes a good life? Lessons from the longest study on happiness | Robert Waldinger](https://i.ytimg.com/vi/8KkKuTCFvzI/default.jpg)
![How to sound smart in your TEDx Talk | Will Stephen | TEDxNewYork](https://i.ytimg.com/vi/8S0FDjFBj8o/default.jpg)
![But what is a neural network? | Chapter 1, Deep learning](https://i.ytimg.com/vi/aircAruvnKk/default.jpg)
![The first 20 hours -- how to learn anything | Josh Kaufman | TEDxCSU](https://i.ytimg.com/vi/5MgBikgcWnY/default.jpg)
![How do you use a custom environment with OpenAI Gym?](https://i.ytimg.com/vi/kd4RrN-FTWY/default.jpg)
![Training a Deep Q-Network - Reinforcement Learning](https://i.ytimg.com/vi/0bt0SjbS3xc/default.jpg)
![AI Learns to Park - Deep Reinforcement Learning](https://i.ytimg.com/vi/VMp6pq6_QjI/default.jpg)
![Mindset changes for success at TU Munich](https://i.ytimg.com/vi/aDA99R6zrCU/default.jpg)
![Deep Q Learning w/ DQN - Reinforcement Learning p.5](https://i.ytimg.com/vi/t3fbETsIBCY/default.jpg)
![High School Quiz Show - The Championship: Advanced Math & Science vs. Lexington (715)](https://i.ytimg.com/vi/6G7c95xhWB4/default.jpg)
![Amazing Science Toys/Gadgets 1](https://i.ytimg.com/vi/l9o33uBi40U/default.jpg)
!["The Billionaire Algorithm" | (it will change your future!)](https://i.ytimg.com/vi/jeqaIYchAI0/default.jpg)
![Lesson 1 - Speak English Clearly! The Imitation Technique](https://i.ytimg.com/vi/T91p6pTPpSY/default.jpg)
![The Secret Knowledge Of Believing](https://i.ytimg.com/vi/1DYmgoij4FQ/default.jpg)
![UNDERSTANDING THE YOUTUBE ALGORITHM AS A SMALL YOUTUBER | How to BEAT the YouTube Algorithm in 2021!](https://i.ytimg.com/vi/Pg6GOUQz20A/default.jpg)