Using communication to reduce locality in distributed multiagent learning

DOI10.1080/095281398146806MaRDI QIDQ4421292zbMATH OpenOpenAlexFDO

Authors Maja J. Matarić

Publication date 2 November 2003

Published in Journal of Experimental & Theoretical Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/095281398146806

zbMATH Keywords

Robotics, Machine Learning, Distributed AI, Multi-agent Systems, Communication Between Agents

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial intelligence for robotics (68T40)

Recommendations

• A distributed learning algorithm for communication development
• Cooperative multi-agent reinforcement learning with constraint-reduced DCOP
• Distributed reinforcement learning for coordinate multi-robot foraging
• Decentralized reinforcement learning of robot behaviors
• scientific article; zbMATH DE number 2243404

Cites work

• Adaption and learning in multi-agent systems. IJCAI '95 workshop, Montréal, Canada, August 21, 1995. Proceedings
• Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development
• The evolution of cooperation

Cited in

(12)

• Convention evolution in organizations and markets
• Decentralized reinforcement learning of robot behaviors
• Self-organisation and communication in groups of simulated and physical robots
• ON HIERARCHICAL CONFIGURATION OF DISTRIBUTED SYSTEMS ON MESH AND HYPERCUBE
• scientific article; zbMATH DE number 1974064 (Why is no real title available?)
• EFFECTS OF COMMUNICATION ON GROUP LEARNING RATES IN A MULTI-AGENT ENVIRONMENT
• Office delivery robot controlled by modular behavior selection networks with planning capability
• A distributed learning algorithm for communication development
• scientific article; zbMATH DE number 2243404 (Why is no real title available?)
• Multi-agent machine learning in self-organizing systems
• Learning multi-agent coordination through connectivity-driven communication
• Imitation guided learning in learning classifier systems

This page was built for publication: Using communication to reduce locality in distributed multiagent learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4421292)