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

• URL: http://arxiv.org/abs/2606.18308v1
• Date: Tue, 16 Jun 2026 07:41:43 GMT
• Title: TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning
• Abstract summary: We show that three features form a directed cycle of biases that defeats any naive composition of off-the-shelf modules.<n>We introduce TRIDENT, the first MARL framework whose three components are co-designed to cancel each leak.<n>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.
• Score: 26.128298844361183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning [1.889930012459364]
  We show that dynamically updating-generated reward weights during off-policy LLML violates the stationarity assumption of Potential-Based Shaping.<n>We propose two stabilisation strategies: a Phase-Based Freeze Schedule that enforces strict stationarity within training phases, and Exponential Moving Average (EMA) smoothing that bounds per-episode weight drift.
  arXiv  Detail & Related papers  (2026-07-05T19:29:21Z)
• Privacy-Preserving Federated Temporal Graph Learning with Digital Twin--Guided Adaptive Deception for Cyber-Resilient IoMT [0.6095710009266794]
  This paper presents the Federated Temporal Graph Convolutional Network with Advantage Actor-Critic (Federated TGCN-A2C)<n>The framework achieves 99.48% and 99.61% test accuracy with weighted-F1 scores of 0.9948 and 0.9961, converging within 25 and 10 federated rounds, outperforming Fed-Inforce-Fusion by 0.21 percentage points while covering three additional attack categories.<n>Post-hoc explainability via SHAP, LIME, Grad-CAM, and counterfactual analysis confirms decisions are grounded in semantically meaningful flow features, supporting regulatory accountability in clinical deployments.
  arXiv  Detail & Related papers  (2026-06-19T15:09:38Z)
• OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization [58.03221830946145]
  We propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes.<n>We show that OmniISR consistently improves model performance in both centralized and federated paradigms.
  arXiv  Detail & Related papers  (2026-05-19T04:13:27Z)
• RVPO: Risk-Sensitive Alignment via Variance Regularization [13.192921543523283]
  We propose Reward-Variance Policy Optimization (RVPO), a risk-sensitive framework that penalizes inter-reward variance during advantage aggregation.<n>We show via Taylor expansion that a LogSumExp (SoftMin) operator effectively acts as a smooth variance penalty.<n>By preventing the model from neglecting difficult constraints to exploit easier objectives, RVPO improves overall scores on HealthBench.
  arXiv  Detail & Related papers  (2026-05-07T06:43:05Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• K-GMRF: Kinetic Gauss-Markov Random Field for First-Principles Covariance Tracking on Lie Groups [8.489406212619164]
  We propose K-GMRF, an online, training-free framework for covariance tracking.<n>Our method interprets observations as torques driving a latent angular velocity, propagated via a structure-preserving symplectic integrator.<n>We theoretically prove that this second-order dynamics achieves zero steady-state error under constant rotation.
  arXiv  Detail & Related papers  (2026-03-20T03:16:36Z)
• DeFRiS: Silo-Cooperative IoT Applications Scheduling via Decentralized Federated Reinforcement Learning [62.347535250646196]
  This paper proposes DeFRiS, a Decentralized Federated Reinforcement Learning framework for robust and scalable Silo-cooperative IoT application scheduling.<n>DeFRiS integrates three innovations: (i) an action-space-agnostic policy utilizing candidate resource scoring to enable seamless knowledge transfer across heterogeneous silos; (ii) a silo-optimized local learning mechanism combining Generalized Advantage Estimation with clipped policy updates to resolve sparse delayed reward challenges; and (iii) a Dual-Track Non-IID robust decentralized aggregation protocol leveraging gradient fingerprints for similarity-aware knowledge transfer and anomaly detection.
  arXiv  Detail & Related papers  (2026-03-16T02:02:38Z)
• MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning [16.012761588513026]
  Reinforcement Learning with Verifiable Rewards (RLVR) algorithms rely on rigid, uniform, and symmetric trust region mechanisms.<n>We propose Mass-Adaptive Soft Policy Optimization (MASPO), a unified framework designed to harmonize these three dimensions.<n> MASPO integrates a differentiable soft Gaussian gating to maximize gradient utility, a mass-adaptive limiter to balance exploration across the probability spectrum, and an asymmetric risk controller to align update magnitudes with signal confidence.
  arXiv  Detail & Related papers  (2026-02-19T17:05:20Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• FP-AbDiff: Improving Score-based Antibody Design by Capturing Nonequilibrium Dynamics through the Underlying Fokker-Planck Equation [19.153777175873547]
  We introduce FP-AbDiff, the first antibody generator to enforce Fokker-Planck Equation (FPE) physics along the entire generative trajectory.<n>By aligning generative dynamics with physical laws, FP-AbDiff enhances robustness and generalizability, establishing a principled approach for physically faithful and functionally viable antibody design.
  arXiv  Detail & Related papers  (2025-11-05T01:44:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.