Internet Archive Scholar
Filters
























1 Hit in 4.2 sec

The Sandbox Environment for Generalizable Agent Research (SEGAR) [article]

R Devon Hjelm, Bogdan Mazoure, Florian Golemo, Felipe Frujeri, Mihai Jalobeanu, Andrey Kolobov
2022 arXiv   pre-print

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (3.1 MB)
https://web.archive.org/web/20220516143857/https://arxiv.org/pdf/2203.10351v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

We built the Sandbox Environment for Generalizable Agent Research (SEGAR) with all of these things in mind.  ...  A broad challenge of research on generalization for sequential decision-making tasks in interactive environments is designing benchmarks that clearly landmark progress.  ...  Acknowledgements We would like to thank Microsoft Research (MSR) for their generous grant to help support this research, fostering collaboration between MSR and Mila: the Quebec AI Institute.  ... 
arXiv:2203.10351v1 fatcat:psujawmxdndkpfqmdazqdcq2yq
Citation

R Devon Hjelm, Bogdan Mazoure, Florian Golemo, Felipe Frujeri, Mihai Jalobeanu, Andrey Kolobov. "The Sandbox Environment for Generalizable Agent Research (SEGAR)." arXiv (2022)