Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates

DOI10.1109/TAC.2020.2995814MaRDI QIDQ4990263zbMATH OpenOpenAlexFDO

Authors Lucas Cassano, Kun Yuan, Ali H. Sayed

Publication date 28 May 2021

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

Full work available at URL https://arxiv.org/abs/1810.07792

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Recommendations

• Partially decentralized reinforcement learning in finite, multi-agent Markov decision processes
• Distributed consensus-based multi-agent temporal-difference learning
• scientific article; zbMATH DE number 2219429
• Finite-Time Convergence Rates of Decentralized Stochastic Approximation With Applications in Multi-Agent and Multi-Task Learning
• Byzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation
• Provably efficient reinforcement learning in decentralized general-sum Markov games
• Achieving Linear Convergence in Distributed Asynchronous Multiagent Optimization
• Distributed multi-agent temporal-difference learning with full neighbor information

Cited in

(6)

• Fully asynchronous policy evaluation in distributed reinforcement learning over networks
• Byzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation
• Decentralized Q-Learning for Stochastic Teams and Games
• Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach
• Distributed consensus-based multi-agent temporal-difference learning
• Distributed policy gradient with variance reduction in multi-agent reinforcement learning

This page was built for publication: Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4990263)