SOURCE-LINKED INTELLIGENCE

Behavioral Cloning Outperforms Entropy-Regularized RL: Critic-Driven Failure of Actor-Critic Methods on Adaptive Tumor Treatment

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Adaptive dosing requires policies that reduce tumor burden without excessive toxicity. Learned dosing policies are typically judged against historical or heuristic comparators, which cannot show whether a policy has found the best behavior available. We instead study a three-population tumor-control ODE in which optimal-control analysis fixes the form of a good schedule -- bang-bang dosing punctuated by a singular arc -- and construct a numerical controller of that form as a proxy for near-optimal behavior. Judged against this reference under a sustained-cure criterion -- 200 consecutive days

Read original source ↗ Open in workspace

recordType

paper

region

Global