linZHank / turtlebot_rl

working on a turtlebot reinforcement learning in Gazebo and with help with a simplified openai_ros package
MIT License
7 stars 2 forks source link

Note

Pre-requisite

Setup Turtlebot Gazebo Simulation Environment

Start Q Learning

  1. Launch learning environment, $ roslaunch turtlebot_rl turtlebot_crib.launch
  2. $ cd /home/yourname/ros_ws/turtlebot_rl/scripts, then $ python crib_nav_qtable.py to start Q learning.

    You can substitute crib_nav_qtable.py into crib_nav_qnet.py to start Q-net learning.

Some notes on debugging original openai_ros package

This repo was created to test the contents in this openai_ros's tutorial. However, may be different configurations were implemented, I made following changes to realize my turtlebot bumping around in the maze.