# Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World

arXiv: https://arxiv.org/abs/2110.05457 · HTML: https://mlsanity.com/paper/2110.05457/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2021.

## Built on by (most cited first, 30 of 71)

- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [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)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control](https://mlsanity.com/paper/2401.16889/) (2024)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)](https://mlsanity.com/paper/2401.08392/) (2024)
- [Coupling Vision and Proprioception for Navigation of Legged Robots](https://mlsanity.com/paper/2112.02094/) (2021)
- [GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots](https://mlsanity.com/paper/2209.05309/) (2022)
- [Prompt a Robot to Walk with Large Language Models](https://mlsanity.com/paper/2309.09969/) (2023)
- [Barkour: Benchmarking Animal-level Agility with Quadruped Robots](https://mlsanity.com/paper/2305.14654/) (2023)
- [DribbleBot: Dynamic Legged Manipulation in the Wild](https://mlsanity.com/paper/2304.01159/) (2023)
- [Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot](https://mlsanity.com/paper/2208.01160/) (2022)
- [Robust and Versatile Bipedal Jumping Control through Reinforcement Learning](https://mlsanity.com/paper/2302.09450/) (2023)
- [Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learning](https://mlsanity.com/paper/2303.01488/) (2023)
- [Autonomous Improvement of Instruction Following Skills via Foundation Models](https://mlsanity.com/paper/2407.20635/) (2024)
- [Adaptive Mobile Manipulation for Articulated Objects In the Open World](https://mlsanity.com/paper/2401.14403/) (2024)
- [Learning Torque Control for Quadrupedal Locomotion](https://mlsanity.com/paper/2203.05194/) (2022)
- [ASID: Active Exploration for System Identification in Robotic Manipulation](https://mlsanity.com/paper/2404.12308/) (2024)
- [Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization](https://mlsanity.com/paper/2311.03351/) (2023)
- [A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning](https://mlsanity.com/paper/2205.05212/) (2022)
- [Continuously Improving Mobile Manipulation with Autonomous Real-World RL](https://mlsanity.com/paper/2409.20568/) (2024)
- [Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies](https://mlsanity.com/paper/2310.16686/) (2023)
- [Learning Visual Quadrupedal Loco-Manipulation from Demonstrations](https://mlsanity.com/paper/2403.20328/) (2024)
- [Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning](https://mlsanity.com/paper/2502.02705/) (2025)
- [Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models](https://mlsanity.com/paper/2410.09163/) (2024)
- [Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models](https://mlsanity.com/paper/2407.02666/) (2024)
- [Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning](https://mlsanity.com/paper/2309.14246/) (2023)

## Abstract (arXiv)

Legged robots are physically capable of traversing a wide range of challenging environments, but designing controllers that are sufficiently robust to handle this diversity has been a long-standing challenge in robotics. Reinforcement learning presents an appealing approach for automating the controller design process and has been able to produce remarkably robust controllers when trained in a suitable range of environments. However, it is difficult to predict all likely conditions the robot will encounter during deployment and enumerate them at training-time. What if instead of training controllers that are robust enough to handle any eventuality, we enable the robot to continually learn in any setting it finds itself in? This kind of real-world reinforcement learning poses a number of challenges, including efficiency, safety, and autonomy. To address these challenges, we propose a practical robot reinforcement learning system for fine-tuning locomotion policies in the real world. We demonstrate that a modest amount of real-world training can substantially improve performance during deployment, and this enables a real A1 quadrupedal robot to autonomously fine-tune multiple locomotion skills in a range of environments, including an outdoor lawn and a variety of indoor terrains.