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

DOI10.1016/j.ejcon.2023.100853zbMath1527.93414MaRDI QIDQ6092463

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

Publication date: 23 November 2023

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

zbMATH Keywords

convergence analysisweak convergencereinforcement learningmulti-agent systemsmulti-task learningdistributed consensusoff-policy learningpolicy gradientactor-critic learningcollaborative networks

Mathematics Subject Classification ID

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

Cites Work

• Multiple-gradient descent algorithm (MGDA) for multiobjective optimization
• Consensus-based decentralized real-time identification of large-scale systems
• Natural actor-critic algorithms
• Distributed Stochastic Approximation: Weak Convergence and Network Design
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• OnActor-Critic Algorithms
• A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
• Multicriteria Optimization
• Distributed consensus-based multi-agent temporal-difference learning
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

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