
Udacity Robotics
Utilization of Deep Q Learning to Train a Robotic Arm to Touch an Object
Full Implementation Using Gazebo, Rviz, and ROS
- Used Deep Q Learning to ensure the gripper of a robotic arm touched an object
- Created a reward function to ensure that training could be accomplished in a low number of iterations
- Utilized LSTM and parameters were tuned to ensure high performance
More details about this project can be seen in the paper attached below.