R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909860682006528 |
|---|---|
| author | Mattson, Connor Raveendra, Varun Novoseller, Ellen Waytowich, Nicholas Lawhern, Vernon J. Brown, Daniel S. |
| author_facet | Mattson, Connor Raveendra, Varun Novoseller, Ellen Waytowich, Nicholas Lawhern, Vernon J. Brown, Daniel S. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_18085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations Mattson, Connor Raveendra, Varun Novoseller, Ellen Waytowich, Nicholas Lawhern, Vernon J. Brown, Daniel S. Robotics Artificial Intelligence Multiagent Systems 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. |
| title | R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations |
| topic | Robotics Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2510.18085 |