Timezone: »

 
Poster
A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
Ramin Hasani · Mathias Lechner · Alexander Amini · Daniela Rus · Radu Grosu

Wed Jul 15 01:00 PM -- 01:45 PM & Thu Jul 16 02:00 AM -- 02:45 AM (PDT) @ None #None
in Poster Session 27 »

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.

Keywords: Architectures · Neuroscience and Cognitive Science · Robotics · Deep Learning - General

Author Information

Ramin Hasani (MIT)
Mathias Lechner (IST Austria)
Alexander Amini (MIT)
Daniela Rus (MIT CSAIL)
Radu Grosu (TU Wien)

More from the Same Authors