Amin Noori - Shahrood University ofTechoo۱ogy, Shahrood
Alireza Alfi - Shahrood University ofTechoo۱ogy, Shahrood

In this paper, we find treatment regimens that minimize the cancer cell count by using a drug for a patient that hasChronic Myelogenous Leukemia (CML). CML is a disease of the hematopoietic stem cells. The goal of this paper is todesign an effective drug-schedule to reduce the number of cancer cells in a time-optimal fashion. To achieve this goal,a Reinforcement Learning (RL), which is ooe of the best unsupervised machine learning algorithms, is applied.Because RL has no need of environment model, i.e. it is model-free; it has absorbed interests duriug the recent years,especially in medical applications. The performance of proposed approach is evaluated by simulating oo amathematical model of drug dosage of CML therapy. Simulation results show the feasibility of the proposed method.

Reinforcement Learning, Chronic Myelogenous Leukemia, Drug Therapy