Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning

DOI10.1016/J.EJCON.2023.100853MaRDI QIDQ6092463zbMATH OpenFDO

Authors Miloš S. Stanković, Marko Beko, Nemanja Ilić, Srdjan S. Stankovic

Publication date 23 November 2023

Published in European Journal of Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.EJCON.2023.100853

zbMATH Keywords

actor-critic learningcollaborative networksconvergence analysisdistributed consensusmulti-agent systemsmulti-task learningoff-policy learningpolicy gradientreinforcement learningweak convergence

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Multi-agent systems (93A16) Consensus (93D50)

Recommendations

• Multi-agent natural actor-critic reinforcement learning algorithms
• Distributed entropy-regularized multi-agent reinforcement learning with policy consensus
• Distributed consensus-based multi-agent temporal-difference learning
• Distributed policy evaluation via inexact ADMM in multi-agent reinforcement learning
• An actor-critic algorithm for constrained Markov decision processes

Cites work

• A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Consensus-based decentralized real-time identification of large-scale systems
• Distributed consensus-based multi-agent temporal-difference learning
• Distributed Stochastic Approximation: Weak Convergence and Network Design
• scientific article; zbMATH DE number 4085440 (Why is no real title available?)
• scientific article; zbMATH DE number 1321699 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• Multicriteria Optimization
• Multiple-gradient descent algorithm (MGDA) for multiobjective optimization
• Natural actor-critic algorithms
• Off-policy learning with eligibility traces: a survey
• OnActor-Critic Algorithms
• Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize

Cited in

(6)

• scientific article; zbMATH DE number 2079783 (Why is no real title available?)
• Multi-actor mechanism for actor-critic reinforcement learning
• Distributed consensus-based multi-agent temporal-difference learning
• On centralized critics in multi-agent reinforcement learning
• Distributed entropy-regularized multi-agent reinforcement learning with policy consensus
• Optimal consensus control for input-delay nonlinear multi-agent systems with input saturation utilizing synchronous integral reinforcement learning

This page was built for publication: Multi-agent off-policy actor-critic algorithm for distributed multi-task reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6092463)