Carview!

CARVIEW

MOTORHOMES

Select Language

HTTP/2 301 server: GitHub.com content-type: text/html location: https://agarwl.github.io/rliable/ x-github-request-id: A3CE:2D64E0:94FDED:A7493F:6952FEC9 accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 22:20:58 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210054-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767046859.748218,VS0,VE199 vary: Accept-Encoding x-fastly-request-id: 43c922e33a5c0fba13ab2f674e75ad8778f2d2ad content-length: 162 HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sat, 09 Apr 2022 22:36:26 GMT access-control-allow-origin: * etag: W/"62520a6a-116b" expires: Mon, 29 Dec 2025 22:30:59 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 3726:444BC:9674AA:A8C113:6952FECA accept-ranges: bytes age: 0 date: Mon, 29 Dec 2025 22:20:59 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210054-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767046859.961431,VS0,VE223 vary: Accept-Encoding x-fastly-request-id: a8cd186ce23d77919c538922c4afbd6905de8214 content-length: 1835 Deep Reinforcement Learning at the Edge of the Statistical Precipice

Our findings call for a change in how we evaluate performance in deep RL, for which we present a more rigorous evaluation methodology, accompanied with an open-source library rliable, to prevent unreliable results from stagnating the field.

Citing

To cite this paper, please use the following reference:

@article{agarwal2021deep,
  title={Deep reinforcement learning at the edge of the statistical precipice},
  author={Agarwal, Rishabh and Schwarzer, Max and Castro, Pablo Samuel and Courville, Aaron C and Bellemare, Marc},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}