Decentralized Learning in Finite Markov Chains: Revisited

DOI10.1109/TAC.2009.2017977MaRDI QIDQ4974666zbMATH OpenOpenAlexFDO

Authors Hyeong Soo Chang

Publication date 8 August 2017

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

Full work available at URL https://doi.org/10.1109/tac.2009.2017977

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Decentralized systems (93A14) Stochastic learning and adaptive control (93E35)

Recommendations

• Decentralized learning in finite Markov chains
• Partially decentralized reinforcement learning in finite, multi-agent Markov decision processes
• Finite-Time Convergence Rates of Decentralized Stochastic Approximation With Applications in Multi-Agent and Multi-Task Learning
• Provably efficient reinforcement learning in decentralized general-sum Markov games
• Decentralized MDPs with sparse interactions
• Finite-Sample Analysis for Decentralized Batch Multiagent Reinforcement Learning With Networked Agents
• Distributed Markov Chain Redesign for Multiagent Decision-Making Problems
• Learning models for decentralized decision making
• Decentralized Learning for Multiplayer Multiarmed Bandits

Cited in

(5)

• Output synchronization control for a class of complex dynamical networks with non-identical dynamics
• Multi-agent zero-sum differential graphical games for disturbance rejection in distributed control
• Adaptive Control and Signal Processing: literature survey (No. 14)
• Optimal model-free output synchronization of heterogeneous systems using off-policy reinforcement learning
• Two-phase selective decentralization to improve reinforcement learning systems with MDP

This page was built for publication: Decentralized Learning in Finite Markov Chains: Revisited

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4974666)