This code performs preference-based GP regression, inference and active query generation.

Companion code to RSS 2020 paper: E Bıyık*, N Huynh*, MJ Kochenderfer, D Sadigh, "Active Preference-Based Gaussian Process Regression for Reward Learning", Proceedings of Robotics: Science and Systems (RSS), Corvallis, Oregon, USA, Jul. 2020.

Dependencies

You need to have the following libraries with Python3:

• NumPy
• SciPy

Running

You simply read test.py to understand how to use the package. For testing, just run

	python test.py

Paper citation

If you used this code or found it helpful, consider citing the following paper:

@inproceedings{biyik2020active,
  title={Active Preference-Based Gaussian Process Regression for Reward Learning},
  author={Biyik, Erdem and Huynh, Nicolas and Kochenderfer, Mykel J. and Sadigh, Dorsa},
  booktitle={Proceedings of Robotics: Science and Systems (RSS)},
  year={2020},
  month={July}
}