paper-with-me

홈 › Papers

Disentangled Control of Multi-Agent Systems

2025-11-08 · Ruoyu Lin, Gennaro Notomista, Magnus Egerstedt arxiv

This paper develops a general framework with convergence guarantees for multi-agent control synthesis, which applies to a wide range of problems, including those with time-varying objective functions. The proposed framework achieves decentralization without inducing entangled dynamics among agents, and it naturally supports multi-objective robotics and real-time implementation. To demonstrate its generality and effectiveness, the framework is applied to three representative problems, namely time-varying leader-follower formation control, decentralized coverage control for time-varying density functions, which is a long-standing open problem, and safe formation navigation in a dense environment.

📄 PDF Abstract BibTeX arXiv:2511.05900

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multi-Agent Reinforcement Learning with Multi-Step Generative Models

2019-01-29 · Orr Krupnik, Igor Mordatch, Aviv Tamar

We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical…

continuous-controlContinuous ControlDecision MakingModel-based Reinforcement Learning+5

DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction

2024-06-30 · Ameya Pore, Riccardo Muradore, Diego Dall'Alba

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper,…

Reinforcement Learning (RL)

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis

2026-07-26 · Xinhao Yao, Yuanzhuo Liu, Changhao Wang, Yunfei Yu 외 arxiv

Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entangles retrieval quality, long-context comp…

GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction

2021-12-01 · NeurIPS 2021 12 · Longyuan Li, Jian Yao, Li Wenliang, Tong He 외

Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems. This is challenging because humans make decisions based on complex social relations and…

DecoderGraph AttentionRelationTrajectory Prediction

Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning

2022-02-28 · Zhifeng Qian, Mingyu You, Hongjun Zhou, Bin He

Goal-conditioned reinforcement learning is a crucial yet challenging algorithm which enables agents to achieve multiple user-specified goals when learning a set of skills in a dynamic environment. However, it typically r…

Positionreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1