paper-with-me

홈 › Papers

TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning

2026-06-16 · Zijie Meng, Ziwei Li, Yufei Liu, Zhiyu Li, Jiyuan Liu, Wenhua Nie, Bingcai Wei, Miao Zhang arxiv

Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics. We show that these three features form a directed cycle of biases that defeats any naive composition of off-the-shelf modules, and formalize this as a three-way coupling lemma. We then introduce TRIDENT, the first MARL framework whose three components are co-designed to cancel each leak: a Richardson-Romberg gradient correction reducing Gumbel-Softmax bias from O(tau) to O(tau^2), a Lyapunov-constrained sequential trust-region update enforcing per-iterate feasibility, and a physics-informed residual critic that decomposes value rather than reward. We prove an O~(1/sqrt(K)) convergence rate to a constrained Nash equilibrium and an O(sqrt(K)) cumulative-violation bound. On multi-UAV mobile-edge computing, autonomous intersection management, and a hybrid SMAC variant, TRIDENT cuts training-time violations by 95.5% over MADDPG and 76.3% over MACPO, while improving reward by 13.5% over the strongest unconstrained baseline.

📄 PDF Abstract BibTeX arXiv:2606.18308

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law

2025-07-22 · Zheng Hui, Yijiang River Dong, Ehsan Shareghi, Nigel Collier arxiv

As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical. While prior work …

TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis

2025-05-30 · Xiaorui Wu, Xiaofeng Mao, Fei Li, Xin Zhang 외

Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes. Although safety alignment datasets have been …

DiversityLanguage ModelingLanguage ModellingLarge Language Model+2

Jailbreaking LLMs via Calibration

2026-01-31 · Yuxuan Lu, Yongkang Guo, Yuqing Kong arxiv

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of saf…

FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning

2026-03-19 · Sheng Liu, Panos Papadimitratos arxiv

FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC). However, by enabling collaboration, FL-based RCC exposes the system to adversarial participants launching Tar…

Federated Learning

Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis

2021-10-25 · Jing Lin, Yu Zhang, Edwin Khoo

Advancing lithium-ion batteries (LIBs) in both design and usage is key to promoting electrification in the coming decades to mitigate human-caused climate change. Inadequate understanding of LIB degradation is an importa…

Prognosis