Reinforcement learning derived chemotherapeutic schedules for robust patient-specific therapy given unknown patient response parameters

When developing a chemotherapeutic dosing schedule for treating cancer in-silico one relies upon a parameterization of a particular tumour growth model to describe the dynamics of the cancer in response to the dose of the drug. It is often prohibitively difficult, in practice, to ensure the validity of patient-specific parameterizations of these models for any particular patient. As a result, sensitivities to these particular parameters can result in therapeutic dosing schedules that are optimal in principle not performing well on particular patients. In this study, we demonstrate that chemotherapeutic dosing strategies learned via reinforcement learning methods are more robust to perturbations in patient-specific parameter values than those learned via classical optimal control methods. By training a reinforcement learning agent on mean-value parameters and allowing the agent access to a more easily measurable metric, relative bone marrow density, we are able to develop drug dosing schedules that outperform schedules learned via classical optimal control methods, even when such methods are allowed to leverage the same bone marrow measurements.