Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

TL;DR

This paper introduces DGPPO, a framework that learns safe, high-performance control policies for multi-agent systems with unknown dynamics, partial observability, and changing neighborhoods, ensuring safety without sacrificing task effectiveness.

Contribution

The paper presents a novel framework that simultaneously learns a distributed graph CBF and a high-performance safe policy for multi-agent systems with complex, unknown dynamics.

Findings

DGPPO achieves high task performance comparable to baseline methods ignoring safety.

DGPPO maintains safety rates comparable to conservative baselines.

The method works across multiple simulation environments with a consistent set of hyperparameters.

Abstract

Control policies that can achieve high task performance and satisfy safety constraints are desirable for any system, including multi-agent systems (MAS). One promising technique for ensuring the safety of MAS is distributed control barrier functions (CBF). However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable. To tackle these challenges, we propose DGPPO, a new framework that simultaneously learns both a discrete graph CBF which handles neighborhood changes and input constraints, and a distributed high-performance safe policy for MAS with unknown discrete-time dynamics. We empirically validate our claims on a suite of multi-agent tasks spanning three different simulation engines. The results suggest that, compared with existing methods, our DGPPO framework obtains policies that achieve high task performance (matching baselines that ignore the safety constraints), and high safety rates (matching the most conservative baselines), with a constant set of hyperparameters across all environments.