Watts: Infrastructure for Open-Ended Learning
Abstract
This paper proposes a framework called Watts for implementing, comparing, and recombining open-ended learning (OEL) algorithms. Motivated by modularity and algorithmic flexibility, Watts atomizes the components of OEL systems to promote the study of and direct comparisons between approaches. Examining implementations of three OEL algorithms, the paper introduces the modules of the framework. The hope is for Watts to enable benchmarking and to explore new types of OEL algorithms. The repo is available at \url{https://github.com/aadharna/watts}
Cite
Text
Dharna et al. "Watts: Infrastructure for Open-Ended Learning." ICLR 2022 Workshops: ALOE, 2022.Markdown
[Dharna et al. "Watts: Infrastructure for Open-Ended Learning." ICLR 2022 Workshops: ALOE, 2022.](https://mlanthology.org/iclrw/2022/dharna2022iclrw-watts/)BibTeX
@inproceedings{dharna2022iclrw-watts,
title = {{Watts: Infrastructure for Open-Ended Learning}},
author = {Dharna, Aaron and Summers, Charlie and Dasari, Rohin and Togelius, Julian and Hoover, Amy K},
booktitle = {ICLR 2022 Workshops: ALOE},
year = {2022},
url = {https://mlanthology.org/iclrw/2022/dharna2022iclrw-watts/}
}