Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?
arXiv:1809.04423
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 Neuronal Circuit Policies (NCPs), defined as the model of biological neural circuits reparameterized for the control of an alternative task. We learn instances of NCPs 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. Neuronal circuit policies perform on par and in some cases surpass the performance of contemporary deep learning models with the advantage leveraging significantly fewer learnable parameters and realizing interpretable dynamics at the cell-level.
arXiv commentarXiv admin note: substantial text overlap with arXiv:1803.08554
References in corpus (7)
- Evolution Strategies as a Scalable Alternative to Reinforcement Learning
- Visualizing and Understanding Recurrent Networks
- Safe Model-based Reinforcement Learning with Stability Guarantees
- Simple random search provides a competitive approach to reinforcement learning
- Liquid Time-constant Recurrent Neural Networks as Universal Approximators
- SIM-CE: An Advanced Simulink Platform for Studying the Brain of Caenorhabditis elegans
- Non-Associative Learning Representation in the Nervous System of the Nematode Caenorhabditis elegans