Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahmad, H. M. Sabbir, Sabouni, Ehsan, Wasilkoff, Alexander, Budhraja, Param, Guo, Zijian, Zhang, Songyuan, Fan, Chuchu, Cassandras, Christos, Li, Wenchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913995027382272
author Ahmad, H. M. Sabbir
Sabouni, Ehsan
Wasilkoff, Alexander
Budhraja, Param
Guo, Zijian
Zhang, Songyuan
Fan, Chuchu
Cassandras, Christos
Li, Wenchao
author_facet Ahmad, H. M. Sabbir
Sabouni, Ehsan
Wasilkoff, Alexander
Budhraja, Param
Guo, Zijian
Zhang, Songyuan
Fan, Chuchu
Cassandras, Christos
Li, Wenchao
contents We address the problem of safe policy learning in multi-agent safety-critical autonomous systems. In such systems, it is necessary for each agent to meet the safety requirements at all times while also cooperating with other agents to accomplish the task. Toward this end, we propose a safe Hierarchical Multi-Agent Reinforcement Learning (HMARL) approach based on Control Barrier Functions (CBFs). Our proposed hierarchical approach decomposes the overall reinforcement learning problem into two levels learning joint cooperative behavior at the higher level and learning safe individual behavior at the lower or agent level conditioned on the high-level policy. Specifically, we propose a skill-based HMARL-CBF algorithm in which the higher level problem involves learning a joint policy over the skills for all the agents and the lower-level problem involves learning policies to execute the skills safely with CBFs. We validate our approach on challenging environment scenarios whereby a large number of agents have to safely navigate through conflicting road networks. Compared with existing state of the art methods, our approach significantly improves the safety achieving near perfect (within 5%) success/safety rate while also improving performance across all the environments.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14850
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
Ahmad, H. M. Sabbir
Sabouni, Ehsan
Wasilkoff, Alexander
Budhraja, Param
Guo, Zijian
Zhang, Songyuan
Fan, Chuchu
Cassandras, Christos
Li, Wenchao
Machine Learning
Artificial Intelligence
Robotics
We address the problem of safe policy learning in multi-agent safety-critical autonomous systems. In such systems, it is necessary for each agent to meet the safety requirements at all times while also cooperating with other agents to accomplish the task. Toward this end, we propose a safe Hierarchical Multi-Agent Reinforcement Learning (HMARL) approach based on Control Barrier Functions (CBFs). Our proposed hierarchical approach decomposes the overall reinforcement learning problem into two levels learning joint cooperative behavior at the higher level and learning safe individual behavior at the lower or agent level conditioned on the high-level policy. Specifically, we propose a skill-based HMARL-CBF algorithm in which the higher level problem involves learning a joint policy over the skills for all the agents and the lower-level problem involves learning policies to execute the skills safely with CBFs. We validate our approach on challenging environment scenarios whereby a large number of agents have to safely navigate through conflicting road networks. Compared with existing state of the art methods, our approach significantly improves the safety achieving near perfect (within 5%) success/safety rate while also improving performance across all the environments.
title Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2507.14850