Distributed consensus-based multi-agent temporal-difference learning

DOI10.1016/j.automatica.2023.110922zbMath1520.93516MaRDI QIDQ6164031

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

Publication date: 30 June 2023

Published in: Automatica (Search for Journal in Brave)

Mathematics Subject Classification ID

Decentralized systems (93A14) Markov and semi-Markov decision processes (90C40) Multi-agent systems (93A16) Consensus (93D50)

Related Items

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

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Application of reinforcement learning to wireless sensor networks: models and algorithms
• Consensus-based decentralized real-time identification of large-scale systems
• Distributed time synchronization for networks with random delays and measurement noise
• Consensus based overlapping decentralized estimation with missing observations and communication faults
• Distributed model based event-triggered control for synchronization of multi-agent systems
• Optimal dynamic formation control of multi-agent systems in constrained environments
• Distributed Stochastic Approximation: Weak Convergence and Network Design
• Distributed Policy Evaluation Under Multiple Behavior Strategies
• On Generalized Bellman Equations and Temporal-Difference Learning
• Distributed asynchronous deterministic and stochastic gradient optimization algorithms
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• Asynchronous Distributed Blind Calibration of Sensor Networks Under Noisy Measurements
• ${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$
• Distributed Reinforcement Learning via Gossip