2018/03/22 by Mathias Lechner, Lechner, Mathias, Ramin Hasani +3 · 1 citation
Decision Sciences · Environmental Science · Social Sciences · #Artificial Intelligence (cs.AI) #Climate Change and Environmental Impact #Diverse Interdisciplinary Research Innovations #Environmental, Ecological, and Cultural Studies #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Neurons and Cognition (q-bio.NC)
paper · pdf · doi:10.48550/arxiv.1803.08554
openalex publication_date 2018/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose an effective way to create interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds. We model the tap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neuronal parameters as a policy for controlling basic RL tasks. We also autonomously park a real rover robot on a pre-defined trajectory, by deploying such neuronal circuit policies learned in a simulated environment. For reconfiguration of the purpose of the TW neural circuit, we adopt a search-based RL algorithm. We show that our neuronal policies perform as good as deep neural network policies with the advantage of realizing interpretable dynamics at the cell level.