Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management

Sanjay Basu, Sadiq Y. Patel, Parth Sheth, Bhairavi Muralidharan, Namrata Elamaran +2 more
9/11/2025
cs.LGcs.AIcs.LO

No official code found. Best implementation: sanjaybasu/fg_farl (1 star, last commit 2025-09-11).

Abstract

We introduce Feasibility-Guided Fair Adaptive Reinforcement Learning (FG-FARL), an offline RL procedure that calibrates per-group safety thresholds to reduce harm while equalizing a chosen fairness target (coverage or harm) across protected subgroups. Using de-identified longitudinal trajectories from a Medicaid population health management program, we evaluate FG-FARL against behavior cloning (BC) and HACO (Hybrid Adaptive Conformal Offline RL; a global conformal safety baseline). We report off-policy value estimates with bootstrap 95% confidence intervals and subgroup disparity analyses with p-values. FG-FARL achieves comparable value to baselines while improving fairness metrics, demonstrating a practical path to safer and more equitable decision support.

View on arXivView PDF

Code Implementations(1)

sanjaybasu/fg_farlCommunity58%

Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management

10TeX, ShellSep 11, 20251 years ago

Similar Papers

Hybrid Adaptive Conformal Offline Reinforcement Learning for Fair Population Health Management

91% match1 repo2025

Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing

86% match2025

Test-Time Learning and Inference-Time Deliberation for Efficiency-First Offline Reinforcement Learning in Care Coordination and Population Health Management

83% match2025

Pragmatic Policy Development via Interpretable Behavior Cloning

82% match1 repo2025

Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications

82% match2023

Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination

82% match1 repo142024

Cite this paper

@article{basu2025feasibilityguided,
  title  = {Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management},
  author = {Sanjay Basu and Sadiq Y. Patel and Parth Sheth and Bhairavi Muralidharan and Namrata Elamaran and Aakriti Kinra and Rajaie Batniji},
  year   = {2025},
  eprint = {2509.09655},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.09655v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.09655.svg)](https://codeofpaper.com/paper/2509.09655)

Discussion