# R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations

arXiv: https://arxiv.org/abs/2510.18085 · HTML: https://mlsanity.com/paper/2510.18085/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 20 Oct 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning](https://mlsanity.com/paper/2109.08273/) (2021)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [Coordinated Multi-Agent Imitation Learning](https://mlsanity.com/paper/1703.03121/) (2017)
- [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://mlsanity.com/paper/2207.03530/) (2022)
- [Multi-Agent Imitation Learning for Driving Simulation](https://mlsanity.com/paper/1803.01044/) (2018)
- [Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision](https://mlsanity.com/paper/2206.14349/) (2022)
- [Controlling Assistive Robots with Learned Latent Actions](https://mlsanity.com/paper/1909.09674/) (2019)
- [MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale](https://mlsanity.com/paper/2409.00134/) (2024)
- [Multi-Agent Imitation Learning: Value is Easy, Regret is Hard](https://mlsanity.com/paper/2406.04219/) (2024)
- [Clone Swarms: Learning to Predict and Control Multi-Robot Systems by Imitation](https://mlsanity.com/paper/1912.02811/) (2019)
- [HeRo 2.0: A Low-Cost Robot for Swarm Robotics Research](https://mlsanity.com/paper/2202.12391/) (2022)
- [Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance](https://mlsanity.com/paper/2401.11378/) (2024)
- [Multi-robot persistent surveillance with connectivity constraints](https://mlsanity.com/paper/1909.07703/) (2019)
- [From One to Many: How Active Robot Swarm Sizes Influence Human Cognitive Processes](https://mlsanity.com/paper/2403.13541/) (2024)
- [Discovery and Deployment of Emergent Robot Swarm Behaviors via Representation Learning and Real2Sim2Real Transfer](https://mlsanity.com/paper/2502.15937/) (2025)
- [Collective Behavior Clone with Visual Attention via Neural Interaction Graph Prediction](https://mlsanity.com/paper/2503.06869/) (2025)
- [Transparency in Multi-Human Multi-Robot Interaction](https://mlsanity.com/paper/2101.10495/) (2021)

## 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)

Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstrations are easy to obtain. While IL has been widely applied to single-robot settings, relatively few studies have addressed the extension of these methods to multi-agent systems, especially in settings where a single human must provide demonstrations to a team of collaborating robots. In this paper, we introduce and study Round-Robin Behavior Cloning (R2BC), a method that enables a single human operator to effectively train multi-robot systems through sequential, single-agent demonstrations. Our approach allows the human to teleoperate one agent at a time and incrementally teach multi-agent behavior to the entire system, without requiring demonstrations in the joint multi-agent action space. We show that R2BC methods match, and in some cases surpass, the performance of an oracle behavior cloning approach trained on privileged synchronized demonstrations across four multi-agent simulated tasks. Finally, we deploy R2BC on two physical robot tasks trained using real human demonstrations.