# Neuronal Circuit Policies

arXiv: https://arxiv.org/abs/1803.08554 · HTML: https://mlsanity.com/paper/1803.08554/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2018.

## Built on by (most cited first, 4 of 4)

- [Neuronal Attention Circuit (NAC) for Representation Learning](https://mlsanity.com/paper/2512.10282/) (2025)
- [Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning](https://mlsanity.com/paper/2605.26061/) (2026)
- [A Photonic-Circuits-Inspired Compact Network: Toward Real-Time Wireless Signal Classification at the Edge](https://mlsanity.com/paper/2106.13865/) (2021)
- [Continuous-Time Machine Learning: A Unified Mathematical Perspective](https://mlsanity.com/paper/2609.16710/) (2026)

## Abstract (arXiv)

We propose an effective way to create interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds. We model the tap-withdrawal (TW) neural circuit of the nematode, C. elegans, a circuit responsible for the worm's reflexive response to external mechanical touch stimulations, and learn its synaptic and neuronal parameters as a policy for controlling basic RL tasks. We also autonomously park a real rover robot on a pre-defined trajectory, by deploying such neuronal circuit policies learned in a simulated environment. For reconfiguration of the purpose of the TW neural circuit, we adopt a search-based RL algorithm. We show that our neuronal policies perform as good as deep neural network policies with the advantage of realizing interpretable dynamics at the cell level.