Belief-Space Control for Personalized Cancer Treatment via Active Inference

[Submitted on 9 Jun 2026 (v1), last revised 17 Jun 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:Cancer treatment is at the core a sequential decision-making problem with partial observability, latent patient heterogeneity, and explicit constraints on the budget for medical measurements. Unlike standard Reinforcement Learning (RL) approaches that control state trajectories, cancer treatments permanently modify patients’ transition dynamics, changing how states evolve over time. We model cancer treatment as a belief-space planning problem using active inference, deriving an expected free-energy objective that unifies goal-directed control and information acquisition under measurement budgets without. We implement this framework using real clinical cancer data from the AACR Project GENIE Biopharma Collaborative dataset. Results on clinical data demonstrate a simultaneous patient categorization and high treatment efficacy, under real measurement and treatment constraints.

Submission history

From: Deniz Sargun [view email]
[v1] Tue, 9 Jun 2026 03:38:53 UTC (1,966 KB)
[v2] Mon, 15 Jun 2026 21:06:44 UTC (1,966 KB)
[v3] Wed, 17 Jun 2026 07:43:15 UTC (1,966 KB)