Deep Q Learning Explained - Making a Self-Driving Car (Part 1)

preview_player
Показать описание
This video explains the concepts behind Deep Q Learning, and this series will apply this to making a self-driving car simulation!

Deep Q Learning is a combination of the reinforcement learning algorithm, Q learning, and Deep learning. Q learning uses 'Q values', which are updated via the Bellman equation, and stored in a table. To allow for large and continuous state spaces, a neural network can be used to approximate the Q values for a state.

  1. Point of Insanity Dev
  2. deep q learning
  3. deep q learning explained
  4. q learning
  5. reinforcement learning
  6. reinforcement learning python
Рекомендации по теме
Deep Q-Networks Explained! 0:10:51

Deep Q-Networks Explained!

Q Learning Explained 0:09:27

Q Learning Explained (tutorial)

Q-Learning Explained - 0:06:48

Q-Learning Explained - Reinforcement Learning Tutorial

Deep Q-Learning/Deep Q-Network 0:34:05

Deep Q-Learning/Deep Q-Network (DQN) Explained | Python Pytorch Deep Reinforcement Learning

What is Q-Learning 0:45:44

What is Q-Learning (back to basics)

Q-Learning Explained - 0:08:38

Q-Learning Explained - A Reinforcement Learning Technique

Deep Q-Learning - 0:10:50

Deep Q-Learning - Combining Neural Networks and Reinforcement Learning

A friendly introduction 0:36:26

A friendly introduction to deep reinforcement learning, Q-networks and policy gradients

Deep Reinforcement Learning 0:10:44

Deep Reinforcement Learning | DRL Explained

Q-Learning: Model Free 0:35:35

Q-Learning: Model Free Reinforcement Learning and Temporal Difference Learning

Deep Reinforcement Learning: 0:21:15

Deep Reinforcement Learning: Neural Networks for Learning Control Laws

Deep Q Learning 0:38:55

Deep Q Learning is Simple with PyTorch | Full Tutorial 2020

Reinforcement Learning: Crash 0:11:28

Reinforcement Learning: Crash Course AI #9

Q-learning - Explained! 0:11:54

Q-learning - Explained!

MIT 6.S191 (2023): 0:57:33

MIT 6.S191 (2023): Reinforcement Learning

[Classic] Playing Atari 0:39:12

[Classic] Playing Atari with Deep Reinforcement Learning (Paper Explained)

Overview of Deep 0:24:50

Overview of Deep Reinforcement Learning Methods

Deep Q Learning 0:09:47

Deep Q Learning for Video Games - The Math of Intelligence #9

Reinforcement Learning, by 0:18:19

Reinforcement Learning, by the Book

Reinforcement Learning from 0:08:25

Reinforcement Learning from scratch

MIT 6.S091: Introduction 1:07:30

MIT 6.S091: Introduction to Deep Reinforcement Learning (Deep RL)

AI Learns to 0:08:40

AI Learns to Walk (deep reinforcement learning)

Q Learning simply 0:09:46

Q Learning simply explained | SARSA and Q-Learning Explanation

An introduction to 0:19:50

An introduction to Policy Gradient methods - Deep Reinforcement Learning

Комментарии
Автор

I understood all what I read before with your video, I would love to see more tuning details like: how much steps for episode, what happens in rollouts and optimal update numbers calculations

archlinuxdeveloper
Автор

I didn't really know how to express my thoughts succinctly, so here are all my thoughts.

There is a lack of clear connection between the topics, which both makes it more difficult to remember, and makes it harder to reason about how they could come together.

To give an example of what I'm talking about, consider the Bellman Optimality Equation. You show the full equation and the definition of each of its parts, but the definition of those parts comes 2 minutes later.

To better your videos in the future, I hope you can figure out how to present all the information in a way that builds on itself, as opposed to presenting it in a way that forces the viewer to pick up the pieces and assemble it themselves.

Fixing the above issues would no doubt greatly improve this video, but it is by no means a simple task. Learning how to deliver information in an understandable way is one of the most important skills for an educator of any sort, I don't expect you to get better at it over night. Most super useful skills don't come easy. I liked the pacing and the placement of the text, as well as the simplicity of some of the definitions. You can improve beyond your imagination if you just keep trying your hardest.

benmichaelis