This script can be used for the research of robotic reinforcement learning. The script builds a simulation environment for robot manipulation about pick and place based on the pybullet simulation environment. Users can incorporate this environment into the reinforcement learning algorithm for online data collection and performance evaluation.
The code was tested on Linux with Python3.6. Use of virtualenvs is recommended. To run:
pip install -r requirements.txt
python main.py
![image] (https://github.com/cb614611757/Kuka_Pybullet-for-pick-and-place/blob/master/data/train_image/pick_and_place.png)