Co-Imitation: Learning Design and Behaviour by Imitation
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 46 references that are in the map. First posted on arXiv 2 Sep 2022.
Builds on
27 of 46 references.
References · 27
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2016OpenAI Gymcited by 1,684
- 2016Generative Adversarial Imitation Learningcited by 1,576
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
- 2018A Tutorial on Bayesian Optimizationcited by 734
- 2018An Algorithmic Perspective on Imitation Learningcited by 455
- 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 229
- 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 188
- 2019Efficient Exploration via State Marginal Matchingcited by 186
- 2021Embodied Intelligence via Learning and Evolutioncited by 154
15 more
- 2020Primal Wasserstein Imitation Learningcited by 120
- 2019End-to-End Robotic Reinforcement Learning without Reward Engineeringcited by 115
- 2019State Alignment-based Imitation Learningcited by 73
- 2021What Matters for Adversarial Imitation Learning?cited by 70
- 2020f-IRL: Inverse Reinforcement Learning via State Marginal Matchingcited by 67
- 2018Reinforcement Learning for Improving Agent Designcited by 55
- 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 51
- 2021Cross-Domain Imitation Learning via Optimal Transportcited by 49
- 2019Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learningcited by 34
- 2019Data-efficient Learning of Morphology and Controller for a Microrobotcited by 26
- 2020Learning Locomotion Skills in Evolvable Robotscited by 17
- 2021Morpho-evolution with learning using a controller archive as an inheritance mechanismcited by 7
- 2020EVO-RL: Evolutionary-Driven Reinforcement Learningcited by 6
- 2021Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatchcited by 5
- 2021What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networkscited by 2
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.