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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kumar, Saurabh, Jeon, Hong Jun, Lewandowski, Alex, Van Roy, Benjamin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909280503857152
author Kumar, Saurabh
Jeon, Hong Jun
Lewandowski, Alex
Van Roy, Benjamin
author_facet Kumar, Saurabh
Jeon, Hong Jun
Lewandowski, Alex
Van Roy, Benjamin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle The Need for a Big World Simulator: A Scientific Challenge for Continual Learning
Kumar, Saurabh
Jeon, Hong Jun
Lewandowski, Alex
Van Roy, Benjamin
Machine Learning
Artificial Intelligence
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.
title The Need for a Big World Simulator: A Scientific Challenge for Continual Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.02930