Closed-loop control of in vitro neuronal activity using reinforcement learning after in silico pre-training
TL;DR
In silico-to-in vitro transfer strategy that achieves efficient state-dependent control of network bursting in cultured neurons is demonstrated and it is demonstrated that effective control policies can be derived in biophysically calibrated digital twins and transferred directly to living networks.
Abstract
Controlling specific neuronal dynamics with electrical stimulation is critical for therapeutic neuromodulation, yet deriving optimal control policies remains challenging due to the complex and non-stationary nature of biological neuronal networks. While reinforcement learning (RL) offers a powerful closed-loop control framework, its reliance on prolonged stimulus-driven exploration is difficult to reconcile with the physiological limits of living tissue. Here, we demonstrate an in silico-to-in vitro transfer strategy that achieves efficient state-dependent control of network bursting in cultured neurons. The transferred policy outperforms heuristic controls, while maintaining constrained stimulation usage. Concurrent calcium imaging reveals the mechanistic basis of the learned policy: the agent optimizes stimulation spatially and temporally, exploiting local network topology and intrinsic physiological temporal dynamics. These results establish in vitro brain-on-chip cultures as a tractable stepping stone for RL-based neuromodulation and demonstrate that effective control policies can be derived in biophysically calibrated digital twins and transferred directly to living networks.