diff --git a/readme.md b/readme.md index 8c3b24a67f57d0979a5ec1eb3988f42e315b6dbd..e6eb567aa08bbb87556cd5bdbbca144d2d8b1ee9 100644 --- a/readme.md +++ b/readme.md @@ -1,24 +1,33 @@ -# Xi-learning +# Xi-Learning -Source Code for the Paper "Xi-learning: Successor Feature Transfer Learning for General Reward Functions". +Source code of the Xi-Learning framework and its experimental evaluation for the paper: [Xi-learning: Successor Feature Transfer Learning for General Reward Functions](https://www.arxiv.org). + +Authors: [Chris Reinke](https://www.scirei.net/), [Xavier Alameda-Pineda](http://xavirema.eu/) -Authors: Chris Reinke, Xavier Alameda-Pineda Copyright: INRIA, 2021 + License: GNU General Public License v3.0 or later +<!-- ## Introduction + +Xi-Learning is a Reinforcement Learning framework for Transfer Learning between tasks that differ in their reward functions. +It is based on the concept of Successor Features. +Xi agents learn --> + + ## Setup Requirements: - - >= Python 3.6. + - Python 3.6 or higher. - Linux (developed under Ubuntu 18.04) or MacOS. - Several python package are required which will be automatically installed during the setup. -To run the experiments the xi_learning package must be installed. -It is recommended to install the package in developer mode (*-e*), so that changes to the source code can be directly applied: +To run the experiments the xi_learning python package must be installed. +It is recommended to install the package in developer mode (*-e*), so that changes to the source code can be directly used without the need to reinstall the package: `pip install -e .` -For loading the results with our DataLoader widget in Jupyter notebook, run the following command. +To be able to load the results with our DataLoader widget in Jupyter notebook, run the following command. (Note: The GUI is currently only tested for Jupyter notebooks. For Jupyterlab, other installation procedures are necessary.) `jupyter nbextension enable --py --sys-prefix qgrid`