Disentangled Control of Multi-Agent Systems
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Multi-Agent Reinforcement Learning with Multi-Step Generative Models
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+5DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction
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
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
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 PredictionWeakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
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