This project is carried out by Social Robotics Lab at Uppsala University. We aim to build a system social robotics learning. Currently, this project is at its very initial stage. The README.md is still under development.
At current stage, we aim to find a way to train pepper using Deep Q Network.
You can use
coa blue-coast-py27
python blue-coast.py pepper-v0 -a config/dqn-conf.json -n config/dqn-network.json
to run the first example after install all the sub-modules.
Currently, we need to find a way to map the camera's image to the input of the face_recognition module.
python camera.py 130.238.17.115 9559
In order to run the program, you need to have a look at development.sh to prepare for the environment.
When the installation script is ready, one can use the example code in ./development.sh to install the prerequisite.
./development.sh
Explain how to run the automated tests for this system
Explain what these tests test and why
Give an example
Explain what these tests test and why
Give an example
Add additional notes about how to deploy this on a live system
- Tensorforce - The Torsorflow-based framework for deep reinforcment learning.
- Gym - Deep reinforcement learning environment library
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.
We use SemVer for versioning. For the versions available, see the tags on this repository.
- Alex Yuan Gao - Initial work - BlueCoast
See also the list of contributors who participated in this project.
This project is licensed under the MIT License - see the LICENSE.md file for details
- Uppsala University
- SSF Coin Porject