{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neuronal-circuit-policies","title":"Neuronal Circuit Policies","arxiv_id":"1803.08554","date":"2018-03-22","proceeding":null,"authors":["Mathias Lechner","Ramin M. Hasani","Radu Grosu"],"abstract":"We propose an effective way to create interpretable control agents, by\nre-purposing the function of a biological neural circuit model, to govern\nsimulated and real world reinforcement learning (RL) test-beds. We model the\ntap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit\nresponsible for the worm's reflexive response to external mechanical touch\nstimulations, and learn its synaptic and neuronal parameters as a policy for\ncontrolling basic RL tasks. We also autonomously park a real rover robot on a\npre-defined trajectory, by deploying such neuronal circuit policies learned in\na simulated environment. For reconfiguration of the purpose of the TW neural\ncircuit, we adopt a search-based RL algorithm. We show that our neuronal\npolicies perform as good as deep neural network policies with the advantage of\nrealizing interpretable dynamics at the cell level.","url_abs":"http://arxiv.org/abs/1803.08554v1","url_pdf":"http://arxiv.org/pdf/1803.08554v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neuronal-circuit-policies","repo_url":"https://github.com/mlech26l/neuronal_circuit_policies","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}