Learning Adaptive Safety for Multi-Agent Systems

TL;DR

This paper introduces ASRL, an adaptive safe reinforcement learning framework that automatically optimizes control barrier functions and policies to ensure safety and performance in multi-agent systems with diverse behaviors.

Contribution

The paper presents a novel adaptive safe RL method that automates CBF tuning and policy optimization, improving safety and scalability in multi-agent environments.

Findings

ASRL maintains cost violations below desired limits.

ASRL outperforms existing methods in multi-robot and racing scenarios.

The approach generalizes well to out-of-distribution scenarios.

Abstract

Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing promise for safety assurance but current methods make strong assumptions about other agents and often rely on manual tuning to balance safety, feasibility, and performance. In this work, we delve into the problem of adaptive safe learning for multi-agent systems with CBF. We show how emergent behavior can be profoundly influenced by the CBF configuration, highlighting the necessity for a responsive and dynamic approach to CBF design. We present ASRL, a novel adaptive safe RL framework, to fully automate the optimization of policy and CBF coefficients, to enhance safety and long-term performance through reinforcement learning. By directly interacting with the other agents, ASRL learns to cope with diverse agent behaviours and maintains the cost violations below a desired limit. We evaluate ASRL in a multi-robot system and a competitive multi-agent racing scenario, against learning-based and control-theoretic approaches. We empirically demonstrate the efficacy and flexibility of ASRL, and assess generalization and scalability to out-of-distribution scenarios. Code and supplementary material are public online.