Reinforcement learning for policymaking in epidemic control: A scoping review
Oleksandr Bolshov, Dmytro Chumachenko · 2026
Read Reinforcement learning for policymaking in epidemic control: A scoping review by Oleksandr Bolshov, Dmytro Chumachenko (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351176.txt.
Description
Oleksandr Bolshov and Dmytro Chumachenko reviewed how reinforcement learning, where software learns by trial and reward, has been used to design epidemic controls. Fast moving outbreaks outpace fixed rules. Thirteen studies from 2014 to 2025 passed their screen across four databases plus reference lists. Models split between simple compartment maths and agent simulations of single people.
Most studies set rewards as a trade off between disease harm and social or economic cost. Actions were usually stepped restriction levels, like school closures by tier. Methods and reporting varied widely, which blocks fair comparison. Standard reporting and shared test outbreaks, the authors urge, are needed before learning based policy can be trusted in a real crisis.
Catalog record
| CREATOR | Oleksandr Bolshov, Dmytro Chumachenko |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77694 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |