Watts: Infrastructure for Open-Ended Learning

TL;DR

Watts is a modular framework designed to facilitate implementation, comparison, and development of open-ended learning algorithms, promoting benchmarking and innovation in the field.

Contribution

It introduces a modular architecture for open-ended learning systems, enabling flexible experimentation and systematic comparison of different approaches.

Findings

Framework successfully modularizes OEL components

Enables benchmarking of multiple OEL algorithms

Supports exploration of new OEL algorithm types

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}