Title: The Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
Authors: Hasani, Ramin  
Lechner, Mathias 
Alexander Amini 
Daniela Rus 
Grosu, Radu 
Keywords: Deep Learning; Machine Learning; Artificial Intelligence; biological neural networks; Robotics; Reinforcement learning; interpretable AI
Issue Date: 31-Jul-2020
Book Title: Proceedings of the 37th International Conference on Machine Learning (ICML 2020), Vienna, Austria, PMLR 119, 2020 
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.
URI: http://hdl.handle.net/20.500.12708/15629
http://dx.doi.org/10.34726/241
DOI: 10.34726/241
Organisation: E191-01 - Forschungsbereich Cyber-Physical Systems 
License: Urheberrechtsschutz 1.0
Publication Type: Exhibition Contribution
Inproceedings
Konferenzbeitrag
Appears in Collections:Beitrag in Konferenzband | Conference Paper

Files in this item:

File Description SizeFormat
icml2020_tw (2).pdfPaper2.28 MBAdobe PDF View/Open
supplementary_materials (4).pdfSupplementary Material2.04 MBAdobe PDF View/Open
Show full item record

Google ScholarTM

Check


Items in reposiTUm are protected by copyright, with all rights reserved, unless otherwise indicated.