# Meta Reinforcement Learning for Optimal Design of Legged Robots

arXiv: https://arxiv.org/abs/2210.02750 · HTML: https://mlsanity.com/paper/2210.02750/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 31 references that are in the map.
- First posted on arXiv 6 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Learning robust perceptive locomotion for quadrupedal robots in the wild](https://mlsanity.com/paper/2201.08117/) (2022)
- [Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning](https://mlsanity.com/paper/1511.06342/) (2015)
- [Meta-Reinforcement Learning of Structured Exploration Strategies](https://mlsanity.com/paper/1802.07245/) (2018)
- [Reinforcement Learning for Improving Agent Design](https://mlsanity.com/paper/1810.03779/) (2018)
- [A Versatile Co-Design Approach For Dynamic Legged Robots](https://mlsanity.com/paper/2103.04660/) (2021)

## Built on by (most cited first, 13 of 13)

- [DeepCPG Policies for Robot Locomotion](https://mlsanity.com/paper/2302.13191/) (2023)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Structural Optimization of Lightweight Bipedal Robot via SERL](https://mlsanity.com/paper/2408.15632/) (2024)
- [Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery](https://mlsanity.com/paper/2510.22336/) (2025)
- [Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian Optimization](https://mlsanity.com/paper/2603.18408/) (2026)
- [MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation](https://mlsanity.com/paper/2407.17502/) (2024)
- [Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulation](https://mlsanity.com/paper/2602.17921/) (2026)
- [Path Planning and Reinforcement Learning-Driven Control of On-Orbit Free-Flying Multi-Arm Robots](https://mlsanity.com/paper/2603.23182/) (2026)
- [GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control](https://mlsanity.com/paper/2504.09997/) (2025)
- [Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action Spaces](https://mlsanity.com/paper/2508.14102/) (2025)
- [RobotDesignGPT: Automated Robot Design Synthesis using Vision Language Models](https://mlsanity.com/paper/2601.11801/) (2026)
- [GLAMDRING: Gait Learning And Morphology co-Design via Reinforcement LearnING of CPGs](https://mlsanity.com/paper/2609.19452/) (2026)
- [PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation](https://mlsanity.com/paper/2610.19615/) (2026)

## Abstract (arXiv)

The process of robot design is a complex task and the majority of design decisions are still based on human intuition or tedious manual tuning. A more informed way of facing this task is computational design methods where design parameters are concurrently optimized with corresponding controllers. Existing approaches, however, are strongly influenced by predefined control rules or motion templates and cannot provide end-to-end solutions. In this paper, we present a design optimization framework using model-free meta reinforcement learning, and its application to the optimizing kinematics and actuator parameters of quadrupedal robots. We use meta reinforcement learning to train a locomotion policy that can quickly adapt to different designs. This policy is used to evaluate each design instance during the design optimization. We demonstrate that the policy can control robots of different designs to track random velocity commands over various rough terrains. With controlled experiments, we show that the meta policy achieves close-to-optimal performance for each design instance after adaptation. Lastly, we compare our results against a model-based baseline and show that our approach allows higher performance while not being constrained by predefined motions or gait patterns.