Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research

TL;DR

This paper proposes that multi-agent social interactions create an intrinsic, self-driven curriculum, called an autocurriculum, which fosters continuous innovation through evolving social challenges and adaptive responses.

Contribution

It introduces the concept of autocurricula as an emergent dynamic in multi-agent systems, highlighting its role in promoting ongoing innovation and complexity.

Findings

Social interactions generate an emergent curriculum that drives innovation.

Autocurricula lead to increasingly complex challenges over time.

Multi-agent dynamics can produce continuous adaptive evolution.

Abstract

Evolution has produced a multi-scale mosaic of interacting adaptive units. Innovations arise when perturbations push parts of the system away from stable equilibria into new regimes where previously well-adapted solutions no longer work. Here we explore the hypothesis that multi-agent systems sometimes display intrinsic dynamics arising from competition and cooperation that provide a naturally emergent curriculum, which we term an autocurriculum. The solution of one social task often begets new social tasks, continually generating novel challenges, and thereby promoting innovation. Under certain conditions these challenges may become increasingly complex over time, demanding that agents accumulate ever more innovations.