Watts: Infrastructure for Open-Ended Learning

Aaron Dharna, Charlie Summers, Rohin Dasari, Julian Togelius, Amy K Hoover

Keywords: Open-Ended Learning, Unsupervised Environment Design, Evolutionary Computation, Reinforcement Learning

TL;DR: We built tools to easily implement open-ended learning algorithms.

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}

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2204.13250/code)