Improving coordination in small-scale multi-agent deep reinforcement learning through memory-driven communication

DOI10.1007/s10994-019-05864-5OpenAlexW3100019413WikidataQ126308537 ScholiaQ126308537MaRDI QIDQ2217433

Giovanni Montana, Emanuele Pesce

Publication date: 29 December 2020

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.03887

zbMATH Keywords

artificial neural networksreinforcement learningmulti-agent systems

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

A leader-following paradigm based deep reinforcement learning method for multi-agent cooperation games, Learning multi-agent coordination through connectivity-driven communication

Uses Software

• Python
• PyTorch
• Adam

Cites Work

• Unnamed Item
• Synchronization in networks of identical linear systems
• Elevator group control using multiple reinforcement learning agents
• Forward induction in coordination games
• Consensus in multi-agent systems with communication constraints
• Distributed coordination architecture for multi-robot formation control
• Consensus and Cooperation in Networked Multi-Agent Systems
• Network Topology and Communication Data Rate for Consensusability of Discrete-Time Multi-Agent Systems