8 papers
Node bipartition for rigidity and localization of networks with heterogeneous sensing
Yongjie Liu, Gangshan Jing, Long Wang
Graph rigidity theory is an important tool for examining the solvability of sensor network localization (SNL) problems, and ensuring global convergence of localization algorithms.…
Signed Angle Rigid Graphs for Network Localization and Formation Control
Jinpeng Huang, Gangshan Jing
Graph rigidity theory studies the capability of a graph embedded in the Euclidean space to constrain its global geometric shape via local constraints among nodes and edges, and has…
Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning
Jianglin Ding, Jingcheng Tang, Gangshan Jing
Action-dependent individual policies, which incorporate both environmental states and the actions of other agents in decision-making, have emerged as a promising paradigm for achie…
Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph
Gangshan Jing, He Bai, Jemin George +2
Existing distributed cooperative multi-agent reinforcement learning (MARL) frameworks usually assume undirected coordination graphs and communication graphs while estimating a glob…
Learning Distributed Stabilizing Controllers for Multi-Agent Systems
Gangshan Jing, He Bai, Jemin George +2
We address the problem of model-free distributed stabilization of heterogeneous multi-agent systems using reinforcement learning (RL). Two algorithms are developed. The first algor…
Decomposability and Parallel Computation of Multi-Agent LQR
Gangshan Jing, He Bai, Jemin George +1
Individual agents in a multi-agent system (MAS) may have decoupled open-loop dynamics, but a cooperative control objective usually results in coupled closed-loop dynamics thereby m…