Decentralized Stochastic Control with Partial History Sharing: A Common Information Approach

DOI10.1109/TAC.2013.2239000zbMath1369.90187OpenAlexW1991888757MaRDI QIDQ5353257

Demosthenis Teneketzis, Ashutosh Nayyar, Aditya Mahajan

Publication date: 8 September 2017

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tac.2013.2239000

Mathematics Subject Classification ID

Decentralized systems (93A14) Markov and semi-Markov decision processes (90C40) Stochastic systems in control theory (general) (93E03) Information theory (general) (94A15)

Related Items (22)

Upper and lower values in zero-sum stochastic games with asymmetric information ⋮ A Framework for Studying Decentralized Bayesian Learning with Strategic Agents ⋮ Controller architectures: tradeoffs between performance and structure ⋮ Decentralized stochastic control ⋮ Team Theory and Information Structures of Stochastic Dynamic Decentralized Decision ⋮ Signaling of Information ⋮ Decentralized control for multi-sensors networked systems with different transmission delays and packet dropouts ⋮ Rethinking formal models of partially observable multiagent decision making ⋮ Existence of Team-Optimal Solutions in Static Teams with Common Information: A Topology of Information Approach ⋮ A multi-step estimation approach for optimal control strategies of interconnected systems with weakly connected topology ⋮ Partially observed optimal control of local and remote controllers ⋮ An algorithmic approach to identify irrelevant information in sequential teams ⋮ Provably efficient reinforcement learning in decentralized general-sum Markov games ⋮ Dynamic games among teams with delayed intra-team information sharing ⋮ Separation of learning and control for cyber-physical systems ⋮ Differential privacy optimal control with asymmetric information structure ⋮ A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control ⋮ Unnamed Item ⋮ Asymmetric information control for stochastic systems with different intermittent observations ⋮ Optimal mean decentralized controller design of interconnected systems with randomized information pattern ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms ⋮ Signaling for decentralized routing in a queueing network

This page was built for publication: Decentralized Stochastic Control with Partial History Sharing: A Common Information Approach