Watts: Infrastructure for Open-Ended Learning
This work provides infrastructure for researchers in open-ended learning, but it is incremental as it focuses on modularity and comparison rather than novel algorithmic breakthroughs.
The paper introduces Watts, a modular framework for implementing, comparing, and recombining open-ended learning algorithms, aiming to facilitate benchmarking and exploration of new approaches in this field.
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}