Adaptive queue management in healthcare using supervised Q-learning with time-varying reward and cost structures
Kartick Bag, Raj Panda, Sweety Suman Jha, Arista Lahiri, Debjani Chakraborty · 2026
Read Adaptive queue management in healthcare using supervised Q-learning with time-varying reward and cost structures by Kartick Bag, Raj Panda, Sweety Suman Jha, Arista Lahiri, Debjani Chakraborty (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/PMC13518973.txt.
Description
Kartick Bag and four colleagues build a 2026 learning system for managing hospital outpatient queues as demand swings through the day. Fixed staffing models assume steady arrivals and identical servers, while real clinics see surges plus different handling for first-time and returning patients. Their model separates those two provider types and lets arrivals follow a time-varying pattern.
A Q-learning agent, guided by a supervised exploration rule, decides when to add or move providers. Separate value tables for arrivals and departures capture their different costs and rewards, which also shift over time. Simulations showed clear cuts in total waiting time and system cost versus conventional uniform queue models. The design extends to wider hospital resource planning.
Catalog record
| CREATOR | Kartick Bag, Raj Panda, Sweety Suman Jha, Arista Lahiri, Debjani Chakraborty |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 105113 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |