Coding Deep Q-Learning in PyTorch - Reinforcement Learning DQN Code Tutorial Series p.1

👉Check out https://www.mythicinfinity.com
High quality, low cost streaming text-to-speech built for real-time chat.

Learn how to code the Deep Q-Learning (DQN) reinforcement learning algorithm released by DeepMind in their 2015 paper, "Human Level Control Through Reinforcement Learning."

In this video I explain Q Learning at a conceptual level, go over the artificial intelligence algorithm as presented in the original paper, live code a working implementation of Deep Q Learning, and then train it in the CartPole OpenAI gym environment.

This is the first video of the "Coding Rainbow Series" where I teach you how to code one of the most sophisticated variants of Deep Q Learning called Rainbow, released in 2017.

Contents
0:00 - Intro
1:05 - Overview of Q Learning
3:14 - Understanding the Algorithm
7:28 - Coding DQN
32:10 - Training on Cartpole

Видео Coding Deep Q-Learning in PyTorch - Reinforcement Learning DQN Code Tutorial Series p.1 канала brthor