← 研踪 PaperTrailarXiv:2606.20197 · v4
Stable Transformer-Actor-Critic Model Predictive Control: A Contraction Analysis Approach
首次提交 2026-06-18 21:11
版本更新 2026-11-16 03:48
雷达观测 2026-11-17 17:12
摘要
Hybrid optimization-learning frameworks, such as Actor-Critic Model Predictive Control (MPC), rely on dynamically adjusting cost parameters to manage complex control landscapes. In this paper, we introduce a certifiably robust Transformer-Actor-Critic MPC architecture that leverages history-aware sequence models to shape local optimization while maintaining strict physical safety guarantees. First, we mathematically constrain the Transformer sequence models to satisfy global incremental Input-to-State Stability (ISS). Second, we integrate these neural Lipschitz bounds with Riemannian contraction theory, deriving a novel coupled small-gain condition that enforces uniform closed-loop contraction stability across the interconnected system. Evaluated on quadrotor control and decentralized multi-agent navigation tasks subjected to severe observation noise and process disturbances, our closed-loop stable formulation successfully translates theoretical bounds into physical safety.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v4 · 2026-11-16 03:48 · 最新观测版本
Stable Transformer-Actor-Critic Model Predictive Control: A Contraction Analysis Approach
Hybrid optimization-learning frameworks, such as Actor-Critic Model Predictive Control (MPC), rely on dynamically adjusting cost parameters to manage complex control landscapes. In this paper, we introduce a certifiably robust Transformer-Actor-Critic MPC architecture that leverages history-aware sequence models to shape local optimization while maintaining strict physical safety guarantees. First, we mathematically constrain the Transformer sequence models to satisfy global incremental Input-to-State Stability (ISS). Second, we integrate these neural Lipschitz bounds with Riemannian contraction theory, deriving a novel coupled small-gain condition that enforces uniform closed-loop contraction stability across the interconnected system. Evaluated on quadrotor control and decentralized multi-agent navigation tasks subjected to severe observation noise and process disturbances, our closed-loop stable formulation successfully translates theoretical bounds into physical safety.
查看此版本解读 →查看此版本原文 ↗