The Sandbox Environment for Generalizable Agent Research (SEGAR)

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hjelm, R Devon, Mazoure, Bogdan, Golemo, Florian, Kahou, Samira Ebrahimi, Braga, Pedro, Frujeri, Felipe, Jalobeanu, Mihai, Kolobov, Andrey
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914958110883840
author Hjelm, R Devon
Mazoure, Bogdan
Golemo, Florian
Kahou, Samira Ebrahimi
Braga, Pedro
Frujeri, Felipe
Jalobeanu, Mihai
Kolobov, Andrey
author_facet Hjelm, R Devon
Mazoure, Bogdan
Golemo, Florian
Kahou, Samira Ebrahimi
Braga, Pedro
Frujeri, Felipe
Jalobeanu, Mihai
Kolobov, Andrey
contents A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress. While there has been notable headway, current benchmarks either do not provide suitable exposure nor intuitive control of the underlying factors, are not easy-to-implement, customizable, or extensible, or are computationally expensive to run. We built the Sandbox Environment for Generalizable Agent Research (SEGAR) with all of these things in mind. SEGAR improves the ease and accountability of generalization research in RL, as generalization objectives can be easy designed by specifying task distributions, which in turns allows the researcher to measure the nature of the generalization objective. We present an overview of SEGAR and how it contributes to these goals, as well as experiments that demonstrate a few types of research questions SEGAR can help answer.
format Preprint
id arxiv_https___arxiv_org_abs_2203_10351
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle The Sandbox Environment for Generalizable Agent Research (SEGAR)
Hjelm, R Devon
Mazoure, Bogdan
Golemo, Florian
Kahou, Samira Ebrahimi
Braga, Pedro
Frujeri, Felipe
Jalobeanu, Mihai
Kolobov, Andrey
Machine Learning
A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress. While there has been notable headway, current benchmarks either do not provide suitable exposure nor intuitive control of the underlying factors, are not easy-to-implement, customizable, or extensible, or are computationally expensive to run. We built the Sandbox Environment for Generalizable Agent Research (SEGAR) with all of these things in mind. SEGAR improves the ease and accountability of generalization research in RL, as generalization objectives can be easy designed by specifying task distributions, which in turns allows the researcher to measure the nature of the generalization objective. We present an overview of SEGAR and how it contributes to these goals, as well as experiments that demonstrate a few types of research questions SEGAR can help answer.
title The Sandbox Environment for Generalizable Agent Research (SEGAR)
topic Machine Learning
url https://arxiv.org/abs/2203.10351