The Need for a Big World Simulator: A Scientific Challenge for Continual Learning

TL;DR

This paper emphasizes the importance of developing a high-fidelity, scalable 'big world' simulation environment to advance continual learning research, addressing limitations of existing benchmarks.

Contribution

It formalizes two key criteria for designing future synthetic environments that better reflect real-world continual learning challenges.

Findings

Current benchmarks have unnatural distribution shifts

Existing environments lack fidelity to the 'small agent, big world' concept

Proposes criteria for future environment design

Abstract

The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot store all information that the world has to offer. To perform well, the agent must be carefully designed to ingest, retain, and eject the right information. To enable the development of performant continual learning agents, a number of synthetic environments have been proposed. However, these benchmarks suffer from limitations, including unnatural distribution shifts and a lack of fidelity to the "small agent, big world" framing. This paper aims to formalize two desiderata for the design of future simulated environments. These two criteria aim to reflect the objectives and complexity of continual learning in practical settings while enabling rapid prototyping of algorithms on a smaller scale.