DQN (Deep Q-Network) theory and implementation. Using DQN with ROS and Gazebo.

Показать описание

In this tutorial I explain the basics of the DQN (Deep Q-Network) and how to use it with ROS. We will do a simple cart-pole (inverted pendulum) simulation in Gazebo to see how DQN works.
ROS : Noetic

The project files are here:

Рекомендации по теме

Комментарии

Really nice! I am using Jazzy and Harmonic and tried to rewrite your code for those but have a hard time resetting the model in gazebo during training. When I use the available reset service the model disappears. Have you managed to get it to work in the newer versions?

mikaeltrana

I have downloaded the project file and I have also installed gazebo. How do I run your simulation on my gazebo. I am inserting the path but its not coming on.

collinsokara

I'm new to this and where are you using ros here exactly?
And what projects can i do with only gazebo and very few physical parts
I can code btw

TrueVasember

Can you specify your computer specifications which was used for training

aravindprakash

Hello! Great job on your work! I'm currently working on a similar topic for my master's thesis, and I have a few questions for you:

1) Have you experimented with utilizing the IMU plugin to extract the angle of the pole?
2) Have you explored the use of a plugin to publish to the /cmd_vel topic in order to control the movement of the cart?
3) In your opinion, do you believe that resetting the gazebo environment adequately resets the physical properties of the model, such as forces, gravity, link and joint states back to the initial states?
Thank you in advance!

matiassandacz

hey, trying to follow your code but with a different gazebo environment, can I reach out to you for help?

brendanbrowne

Thank you for your remarkable work and your pedagogy. How can I cite your work?

j_sudi

hello, when trying to load your model I get the error "Could not load controller 'cart_controller' because controller type does not exist
was wondering if you had any clue as to how to go about it

christianvaldes

DQN (Deep Q-Network) theory and implementation. Using DQN with ROS and Gazebo.

DQN (Deep Q-Network) theory and implementation. Using DQN with ROS and Gazebo.

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

Deep Q-Networks (DQNs) in Reinforcement Learning

2) Deep Q Network DQN

Deep Q Networks (DQN)

Deep Q-Network (DQN)

Deep Q Learning Networks

Deep Q-Network (DQN) | Reinforcement Learning (INF8953DE) | Lecture - 7 | Part - 3

Deep Q-Network (DQN)

Q Learning Explained (tutorial)

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

Introduction to TF Agents and Deep Q Learning (Reinforcement learning with TensorFlow Agents)

Reinforcement Learning DQN Algorithm _ training 20k episodes

CS885 Lecture 6b: DQN and TensorFlow (Timmy Tse)

Overview of Deep Reinforcement Learning Methods

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

DQN - Playing Atari with Deep Reinforcement Learning | RL Paper Explained

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

Deep Reinforcement Learning Dueling DQN in Python | TF and Keras | OpenAIGym

Deep Learning Cars

[DQN] Human-level control through deep reinforcement learning (discussions) | AISC Foundational

Deep Reinforcement Learning Double DQN in Python | Keras | OpenAI Gym

Replay Memory Explained - Experience for Deep Q-Network Training

DQN Control for Inverted Pendulum with Reinforcement Learning Toolbox