# Co-Imitation: Learning Design and Behaviour by Imitation

arXiv: https://arxiv.org/abs/2209.01207 · HTML: https://mlsanity.com/paper/2209.01207/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 2 Sep 2022.

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [Efficient Exploration via State Marginal Matching](https://mlsanity.com/paper/1906.05274/) (2019)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [End-to-End Robotic Reinforcement Learning without Reward Engineering](https://mlsanity.com/paper/1904.07854/) (2019)
- [Primal Wasserstein Imitation Learning](https://mlsanity.com/paper/2006.04678/) (2020)
- [State Alignment-based Imitation Learning](https://mlsanity.com/paper/1911.10947/) (2019)
- [What Matters for Adversarial Imitation Learning?](https://mlsanity.com/paper/2106.00672/) (2021)
- [f-IRL: Inverse Reinforcement Learning via State Marginal Matching](https://mlsanity.com/paper/2011.04709/) (2020)
- [Reinforcement Learning for Improving Agent Design](https://mlsanity.com/paper/1810.03779/) (2018)
- [Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning](https://mlsanity.com/paper/1801.01432/) (2018)
- [Cross-Domain Imitation Learning via Optimal Transport](https://mlsanity.com/paper/2110.03684/) (2021)
- [Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning](https://mlsanity.com/paper/1911.06832/) (2019)
- [Data-efficient Learning of Morphology and Controller for a Microrobot](https://mlsanity.com/paper/1905.01334/) (2019)
- [Learning Locomotion Skills in Evolvable Robots](https://mlsanity.com/paper/2010.09531/) (2020)
- [Morpho-evolution with learning using a controller archive as an inheritance mechanism](https://mlsanity.com/paper/2104.04269/) (2021)
- [EVO-RL: Evolutionary-Driven Reinforcement Learning](https://mlsanity.com/paper/2007.04725/) (2020)
- [Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch](https://mlsanity.com/paper/2104.07810/) (2021)
- [What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks](https://mlsanity.com/paper/2111.02371/) (2021)

## Built on by (most cited first, 3 of 3)

- [Towards Embodiment Scaling Laws in Robot Locomotion](https://mlsanity.com/paper/2505.05753/) (2025)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI](https://mlsanity.com/paper/2609.03497/) (2026)

## Abstract (arXiv)

The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.