Comparing On-policy and Off-policy Methods in Reinforcement Learning Using a Simple Simulation

preview_player
Показать описание
In tihs tutorial I am doing experiments using the well-known on-policy and off-policy algorithms to understand their difference.

Ubuntu: 22.04LTS
ROS: Humble
Gazebo-classic

The project is here:

4WS-tutorial
Рекомендации по теме
Комментарии
Автор

Is it possible to modify the code to make the size of obstacles increase over time in maze solving system?

chiyoungkwon
Автор

Thanks for sharing. Can I make it for my custom ros robot

rajmeetsingh
Автор

Hello robot mania. This is Nasr Abdalmanan a PhD student interested in Reinforcement Learning and robotics. I would appreciate if we could meet virtually and discuss few related things. Thanks!

NasrAbdalmanan
visit shbcf.ru