# Neural Circuit Architectural Priors for Quadruped Locomotion

arXiv: https://arxiv.org/abs/2410.07174 · HTML: https://mlsanity.com/paper/2410.07174/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 50 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Distributed Distributional Deterministic Policy Gradients](https://mlsanity.com/paper/1804.08617/) (2018)
- [Emergence of Locomotion Behaviours in Rich Environments](https://mlsanity.com/paper/1707.02286/) (2017)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future](https://mlsanity.com/paper/2001.07092/) (2020)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [Simple random search provides a competitive approach to reinforcement learning](https://mlsanity.com/paper/1803.07055/) (2018)
- [Learning and Transfer of Modulated Locomotor Controllers](https://mlsanity.com/paper/1610.05182/) (2016)
- [Policies Modulating Trajectory Generators](https://mlsanity.com/paper/1910.02812/) (2019)
- [CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion](https://mlsanity.com/paper/2211.00458/) (2022)
- [Symmetry Considerations for Learning Task Symmetric Robot Policies](https://mlsanity.com/paper/2403.04359/) (2024)
- [Deep neuroethology of a virtual rodent](https://mlsanity.com/paper/1911.09451/) (2019)
- [Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking](https://mlsanity.com/paper/2011.07537/) (2020)
- [An Adaptable Approach to Learn Realistic Legged Locomotion without Examples](https://mlsanity.com/paper/2110.14998/) (2021)
- [Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive](https://mlsanity.com/paper/2302.13378/) (2023)
- [Neural Circuit Architectural Priors for Embodied Control](https://mlsanity.com/paper/2201.05242/) (2022)
- [Breaking Symmetries Leads to Diverse Quadrupedal Gaits](https://mlsanity.com/paper/2303.04857/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Causal Framework for Precision Rehabilitation](https://mlsanity.com/paper/2411.03919/) (2024)
- [Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrization](https://mlsanity.com/paper/2604.20365/) (2026)

## Abstract (arXiv)

Learning-based approaches to quadruped locomotion commonly adopt generic policy architectures like fully connected MLPs. As such architectures contain few inductive biases, it is common in practice to incorporate priors in the form of rewards, training curricula, imitation data, or trajectory generators. In nature, animals are born with priors in the form of their nervous system's architecture, which has been shaped by evolution to confer innate ability and efficient learning. For instance, a horse can walk within hours of birth and can quickly improve with practice. Such architectural priors can also be useful in ANN architectures for AI. In this work, we explore the advantages of a biologically inspired ANN architecture for quadruped locomotion based on neural circuits in the limbs and spinal cord of mammals. Our architecture achieves good initial performance and comparable final performance to MLPs, while using less data and orders of magnitude fewer parameters. Our architecture also exhibits better generalization to task variations, even admitting deployment on a physical robot without standard sim-to-real methods. This work shows that neural circuits can provide valuable architectural priors for locomotion and encourages future work in other sensorimotor skills.