# Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion

arXiv: https://arxiv.org/abs/2503.08375 · HTML: https://mlsanity.com/paper/2503.08375/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [Extreme Parkour with Legged Robots](https://mlsanity.com/paper/2309.14341/) (2023)
- [Legged Locomotion in Challenging Terrains using Egocentric Vision](https://mlsanity.com/paper/2211.07638/) (2022)
- [Robot Parkour Learning](https://mlsanity.com/paper/2309.05665/) (2023)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity](https://mlsanity.com/paper/1902.05605/) (2019)
- [Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion](https://mlsanity.com/paper/2202.05481/) (2022)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion](https://mlsanity.com/paper/2409.06366/) (2024)
- [Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controller](https://mlsanity.com/paper/2201.00206/) (2022)
- [Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion](https://mlsanity.com/paper/2310.17634/) (2023)
- [Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning](https://mlsanity.com/paper/2103.06484/) (2021)
- [Learning Agile Locomotion on Risky Terrains](https://mlsanity.com/paper/2311.10484/) (2023)
- [Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization](https://mlsanity.com/paper/2502.07523/) (2025)
- [Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models](https://mlsanity.com/paper/2410.09163/) (2024)
- [Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach](https://mlsanity.com/paper/2409.15755/) (2024)
- [RL-X: A Deep Reinforcement Learning Library (not only) for RoboCup](https://mlsanity.com/paper/2310.13396/) (2023)
- [Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance](https://mlsanity.com/paper/2111.09159/) (2021)
- [A CPG-Based Agile and Versatile Locomotion Framework Using Proximal Symmetry Loss](https://mlsanity.com/paper/2103.00928/) (2021)

## Built on by (most cited first, 8 of 8)

- [XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning](https://mlsanity.com/paper/2509.25174/) (2025)
- [Towards Embodiment Scaling Laws in Robot Locomotion](https://mlsanity.com/paper/2505.05753/) (2025)
- [Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization](https://mlsanity.com/paper/2509.02815/) (2025)
- [Shape Your Body: Value Gradients for Multi-Embodiment Robot Design](https://mlsanity.com/paper/2606.00702/) (2026)
- [Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations](https://mlsanity.com/paper/2510.13488/) (2025)
- [Rapid Embodiment Adaptation for Quadrupedal Locomotion](https://mlsanity.com/paper/2608.01506/) (2026)
- [From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity](https://mlsanity.com/paper/2508.19172/) (2025)
- [OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion](https://mlsanity.com/paper/2609.20566/) (2026)

## Abstract (arXiv)

On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots pose a significant challenge. We present a framework for efficiently learning quadruped locomotion in just 8 minutes of raw real-time training utilizing the sample efficiency and minimal computational overhead of the new off-policy algorithm CrossQ. We investigate two control architectures: Predicting joint target positions for agile, high-speed locomotion and Central Pattern Generators for stable, natural gaits. While prior work focused on learning simple forward gaits, our framework extends on-robot learning to omnidirectional locomotion. We demonstrate the robustness of our approach in different indoor and outdoor environments.