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