Reinforcement Learning-Guided Optogenetic Stimulation Policies for Robust Functional Network Discovery

Optogenetic stimulation has opened up a new avenue to probe neuronal circuitry at high spatiotemporal resolutions. A key challenge in optogenetic stimulation is deciding which subset out of thousands of neurons should be stimulated to elicit a desired network activation or affect behavior. In this work, we introduce a reinforcement learning approach to adaptively narrow down the multitude of stimulation possibilities and robustly identify Granger causal networks that underlie neuronal activity. We use realistic simulations with different underlying circuitry to show the effectiveness of reinforcement learning in identifying an optimal policy for selecting stimulation targets.