Distributed web hacking by adaptive consensus-based reinforcement learning

DOI10.1016/j.artint.2023.104032MaRDI QIDQ6193085

Nemanja Ilić, Unnamed Author, Dejan Dašić, Ranko Petrović, Miljan Vučetić

Publication date: 13 February 2024

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

multi-agent systemdistributed reinforcement learningdistributed Q-learningpenetration testingadaptive consensus-based algorithmcapture the flagethical web hacking

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Internet topics (68M11) Agent technology and artificial intelligence (68T42)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Average consensus on general strongly connected digraphs
• Autonomous agents modelling other agents: a comprehensive survey and open problems
• Fast linear iterations for distributed averaging
• Distributed Stochastic Approximation: Weak Convergence and Network Design
• Optimal Information Security Investment with Penetration Testing
• Directed scale-free graphs
• ${{\cal Q} {\cal D}}$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through ${\rm Consensus} + {\rm Innovations}$
• Broadcast Gossip Algorithms for Consensus on Strongly Connected Digraphs
• Consensus and Cooperation in Networked Multi-Agent Systems

This page was built for publication: Distributed web hacking by adaptive consensus-based reinforcement learning