# Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration

arXiv: https://arxiv.org/abs/2301.06864 · HTML: https://mlsanity.com/paper/2301.06864/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 6 of its 58 references that are in the map.
- First posted on arXiv 17 Jan 2023.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 6 of 6)

- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Inverse Reinforcement Learning in Swarm Systems](https://mlsanity.com/paper/1602.05450/) (2016)
- [Embodied Evolution in Collective Robotics: A Review](https://mlsanity.com/paper/1709.08992/) (2017)
- [Evolution of Collective Behaviors for a Real Swarm of Aquatic Surface Robots](https://mlsanity.com/paper/1511.03154/) (2015)
- [Turing learning: a metric-free approach to inferring behavior and its application to swarms](https://mlsanity.com/paper/1603.04904/) (2016)
- [Understandable Controller Extraction from Video Observations of Swarms](https://mlsanity.com/paper/2209.01118/) (2022)

## Built on by (most cited first, 1 of 1)

- [Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies](https://mlsanity.com/paper/2603.02783/) (2026)

## Abstract (arXiv)

Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, Demo-Cho successfully generated control software to perform four missions. We present results obtained in simulation and with physical robots.