Hasani, R., Lechner, M., Amini, A., Rus, D., & Grosu, R. (2020). The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits. In Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, PMLR 119, 2020. https://doi.org/10.34726/241
E191-01 - Forschungsbereich Cyber-Physical Systems
-
Erschienen in:
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, PMLR 119, 2020
-
Datum (veröffentlicht):
31-Jul-2020
-
Umfang:
12
-
Keywords:
Deep Learning; Machine Learning; Artificial Intelligence; biological neural networks; Robotics; Reinforcement learning; interpretable AI
en
Abstract:
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce ordinary neural circuits (ONCs), defined as the model of biological neural circuits reparameterized for the control of alternative tasks. We first demonstrate that ONCs realize networks with higher maximum flow compared to arbitrary wired networks. We then learn instances of ONCs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Ordinary neural circuits perform on par and, in some cases, significantly surpass the performance of contemporary deep learning models. ONC networks are compact, 77% sparser than their counterpart neural controllers, and their neural dynamics are fully interpretable at the cell-level.
