Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.


Reinforcement learning supercharges redox flow batteries

Designing viable molecular candidates is pivotal to devising low-cost and sustainable storage systems. A reinforcement learning framework has been developed that can identify stable candidates for redox flow batteries in the large search space of organic radicals.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it


Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Radical electrolytes generated with reinforcement learning.


  1. Li, Z. & Lu, Y.-C. Adv. Mater. 32, 2002132 (2020).

    Article  Google Scholar 

  2. S. V., S. S. et al. Nat. Mach. Intell. (2022).

  3. Huskinson, B. et al. Nature 505, 195–198 (2014).

    Article  Google Scholar 

  4. Hollas, A. et al. Nat. Energy 3, 508–514 (2018).

    Article  Google Scholar 

  5. S. V., S. S. et al. Chem. Sci. 12, 13158–13166 (2021).

    Article  Google Scholar 

  6. Sanchez-Lengeling, B. & Aspuru-Guzik, A. Science 361, 360–365 (2018).

    Article  Google Scholar 

  7. Yang, X., Wang, Y., Byrne, R., Schneider, G. & Yang, S. Chem. Rev. 119, 10520–10594 (2019).

    Article  Google Scholar 

  8. Zhavoronkov, A. et al. Nat. Biotechnol. 37, 1038–1040 (2019).

    Article  Google Scholar 

  9. De Luna, P., Wei, J., Bengio, Y., Aspuru-Guzik, A. & Sargent, E. Nature 552, 23–27 (2017).

    Article  Google Scholar 

  10. Seifrid, M., Hattrick-Simpers, J., Aspuru-Guzik, A., Kalil, T. & Cranford, S. Matter 5, 1972–1976 (2022).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding authors

Correspondence to Yang Cao or Alán Aspuru-Guzik.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Cao, Y., Ser, C.T., Skreta, M. et al. Reinforcement learning supercharges redox flow batteries. Nat Mach Intell 4, 667–668 (2022).

Download citation

  • Published:

  • Issue Date:

  • DOI:


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing