Enabling Multi-Robot Collaboration from Single-Human Guidance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ji, Zhengran, Zhang, Lingyu, Sajda, Paul, Chen, Boyuan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916630069510144
author Ji, Zhengran
Zhang, Lingyu
Sajda, Paul
Chen, Boyuan
author_facet Ji, Zhengran
Zhang, Lingyu
Sajda, Paul
Chen, Boyuan
contents Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will emerge. Other studies propose to learn from demonstrations of a group of collaborative experts. Instead, we propose an efficient and explicit way of learning collaborative behaviors in multi-agent systems by leveraging expertise from only a single human. Our insight is that humans can naturally take on various roles in a team. We show that agents can effectively learn to collaborate by allowing a human operator to dynamically switch between controlling agents for a short period and incorporating a human-like theory-of-mind model of teammates. Our experiments showed that our method improves the success rate of a challenging collaborative hide-and-seek task by up to 58% with only 40 minutes of human guidance. We further demonstrate our findings transfer to the real world by conducting multi-robot experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enabling Multi-Robot Collaboration from Single-Human Guidance
Ji, Zhengran
Zhang, Lingyu
Sajda, Paul
Chen, Boyuan
Robotics
Human-Computer Interaction
Machine Learning
Multiagent Systems
Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will emerge. Other studies propose to learn from demonstrations of a group of collaborative experts. Instead, we propose an efficient and explicit way of learning collaborative behaviors in multi-agent systems by leveraging expertise from only a single human. Our insight is that humans can naturally take on various roles in a team. We show that agents can effectively learn to collaborate by allowing a human operator to dynamically switch between controlling agents for a short period and incorporating a human-like theory-of-mind model of teammates. Our experiments showed that our method improves the success rate of a challenging collaborative hide-and-seek task by up to 58% with only 40 minutes of human guidance. We further demonstrate our findings transfer to the real world by conducting multi-robot experiments.
title Enabling Multi-Robot Collaboration from Single-Human Guidance
topic Robotics
Human-Computer Interaction
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2409.19831