A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits
Hasani R, Lechner M, Amini A, Rus D, Grosu R. 2020. A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. Proceedings of the 37th International Conference on Machine Learning. ML: Machine LearningPMLR, PMLR, , 4082–4093.
Download
Download (ext.)
http://proceedings.mlr.press/v119/hasani20a.html
[Published Version]
Conference Paper
| Published
| English
Scopus indexed
Author
Hasani, Ramin;
Lechner, MathiasISTA;
Amini, Alexander;
Rus, Daniela;
Grosu, Radu
Department
Grant
Series Title
PMLR
Abstract
We propose a neural information processing system 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.
Publishing Year
Date Published
2020-01-01
Proceedings Title
Proceedings of the 37th International Conference on Machine Learning
Acknowledgement
RH and RG are partially supported by Horizon-2020 ECSEL Project grant No. 783163 (iDev40), Productive 4.0, and ATBMBFW CPS-IoT Ecosystem. ML was supported in part by the Austrian Science Fund (FWF) under grant Z211-N23
(Wittgenstein Award). AA is supported by the National Science Foundation (NSF) Graduate Research Fellowship
Program. RH and DR are partially supported by The Boeing Company and JP Morgan Chase. This research work is
partially drawn from the PhD dissertation of RH.
Page
4082-4093
Conference
ML: Machine Learning
Conference Location
Virtual
Conference Date
2020-07-12 – 2020-07-18
ISSN
IST-REx-ID
Cite this
Hasani R, Lechner M, Amini A, Rus D, Grosu R. A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. In: Proceedings of the 37th International Conference on Machine Learning. PMLR. ; 2020:4082-4093.
Hasani, R., Lechner, M., Amini, A., Rus, D., & Grosu, R. (2020). A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. In Proceedings of the 37th International Conference on Machine Learning (pp. 4082–4093). Virtual.
Hasani, Ramin, Mathias Lechner, Alexander Amini, Daniela Rus, and Radu Grosu. “A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits.” In Proceedings of the 37th International Conference on Machine Learning, 4082–93. PMLR, 2020.
R. Hasani, M. Lechner, A. Amini, D. Rus, and R. Grosu, “A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits,” in Proceedings of the 37th International Conference on Machine Learning, Virtual, 2020, pp. 4082–4093.
Hasani R, Lechner M, Amini A, Rus D, Grosu R. 2020. A natural lottery ticket winner: Reinforcement learning with ordinary neural circuits. Proceedings of the 37th International Conference on Machine Learning. ML: Machine LearningPMLR, PMLR, , 4082–4093.
Hasani, Ramin, et al. “A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits.” Proceedings of the 37th International Conference on Machine Learning, 2020, pp. 4082–93.
All files available under the following license(s):
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0):
Main File(s)
File Name
2020_PMLR_Hasani.pdf
2.33 MB
Access Level
Open Access
Date Uploaded
2022-01-26
MD5 Checksum
c9a4a29161777fc1a89ef451c040e3b1
Link(s) to Main File(s)
Access Level
Open Access