dawan0111 / ROS2-Reinforcement-Learning-Drive

This repository provides a customizable ROS2 environment for training multiple 2D drive cars using Deep Q-Network (DQN). Currently, agents learn collision-free navigation by avoiding obstacles, but the environment is designed to allow easy modification to train for various objectives in the future.

Repository from Github https://github.comdawan0111/ROS2-Reinforcement-Learning-DriveRepository from Github https://github.comdawan0111/ROS2-Reinforcement-Learning-Drive

This repository is not active

About

This repository provides a customizable ROS2 environment for training multiple 2D drive cars using Deep Q-Network (DQN). Currently, agents learn collision-free navigation by avoiding obstacles, but the environment is designed to allow easy modification to train for various objectives in the future.


Languages

Language:C++ 56.8%Language:Python 39.2%Language:CMake 3.9%