{"ID":2872303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09655","arxiv_id":"2509.09655","title":"Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management","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.","short_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 popula...","url_abs":"https://arxiv.org/abs/2509.09655","url_pdf":"https://arxiv.org/pdf/2509.09655v1","authors":"[\"Sanjay Basu\",\"Sadiq Y. Patel\",\"Parth Sheth\",\"Bhairavi Muralidharan\",\"Namrata Elamaran\",\"Aakriti Kinra\",\"Rajaie Batniji\"]","published":"2025-09-11T17:50:06Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.LO\",\"stat.AP\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}