search

jr-robotics / robo-gym

An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.
https://sites.google.com/view/robo-gym
MIT License
390 stars 74 forks source link

How to use it correctly? #46

Closed KeisukeHamamoto closed 2 years ago

KeisukeHamamoto commented 2 years ago

Hi,

I have a question for you from Japan. First of all, please understand that my English is not good.

I was looking for a reinforcement learning environment. I think robo-gym is the most suitable for my tasks so I want to use it. But I could not use it well so I want to know how to use it from start to end.

In 1st terminal roslaunch ur_robot_server ur_robot_server.launch ur_model:=ur10 gazebo_gui:=true gui:=true In 2nd terminal start-server-manager && attach-to-server-manager In 3rd terminal python3 main.py

I did this but I thought it did not start learning.

matteolucchi commented 2 years ago

Hi @KeisukeHamamoto and thank you for your interest in robo-gym!

There is no need to start roslaunch ur_robot_server ur_robot_server.launch ur_model:=ur10 gazebo_gui:=true gui:=true

It is enough to start the following: terminal 1: start-server-manager && attach-to-server-manager terminal 2: python3 main.py

assuming that main.py is your script.

I hope this helps.

Cheers, Matteo

KeisukeHamamoto commented 2 years ago

Thank you for the quick reply!

I'll try it.