HTTP/2 301 server: GitHub.com content-type: text/html location: https://agarwl.github.io/reincarnating_rl/ x-github-request-id: 5353:2118F1:9AC87C:ADF921:6953758E accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 06:47:44 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210024-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767077264.850552,VS0,VE203 vary: Accept-Encoding x-fastly-request-id: 6cb52452b043fa5117a51a4a17d2faa397d19bb0 content-length: 162 HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sat, 08 Jul 2023 18:52:31 GMT access-control-allow-origin: * etag: W/"64a9b06f-11e1" expires: Tue, 30 Dec 2025 06:57:44 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 088A:318CF6:9AD423:AE02BD:6953758E accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 06:47:44 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210024-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767077264.082573,VS0,VE218 vary: Accept-Encoding x-fastly-request-id: 538e642f40b3fa56d72c7c96aea24a085e309f0a content-length: 1902

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Neural Information Processing Systems (NeurIPS) 2022
Oral at ICML 2022 Updatable ML Workshop

Paper Reference Code Code (CleanRL) Colab Tweetprint Slides Talk Google AI Blog OpenReview Authors

This work argues for an alternative approach to RL research, where we build on prior computational work, which we believe could significantly improve real-world RL adoption and help democratize it further.

Citing

To cite this paper, please use the following reference:

 @article{agarwal2022beyond,
  title={Beyond Tabula Rasa: Reincarnating Reinforcement Learning},
  author={Agarwal, Rishabh and Schwarzer, Max and Castro, Pablo Samuel and Courville, Aaron and Bellemare, Marc G},
  journal={arXiv preprint arXiv:2206.01626},
  year={2022}
}

Authors

Rishabh Agarwal
Google Research, Brain Team and Mila

Max Schwarzer
Mila

Pablo Samuel Castro
Google Research, Brain Team

Aaron Courville
Mila

Marc G. Bellemare
Google Research, Brain Team

For questions, please contact us at: rishabhagarwal@google.com.