Watts: Infrastructure for Open-Ended Learning
Artificial Intelligence
2022-04-29 v1 Machine Learning
Neural and Evolutionary Computing
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
@article{arxiv.2204.13250,
title = {Watts: Infrastructure for Open-Ended Learning},
author = {Aaron Dharna and Charlie Summers and Rohin Dasari and Julian Togelius and Amy K. Hoover},
journal= {arXiv preprint arXiv:2204.13250},
year = {2022}
}
Comments
ICLR Workshop on Agent Learning in Open-Endedness (ALOE 2022)