An improved Q-learning algorithm using synthetic pheromones

DOI10.1007/3-540-45941-3_21MaRDI QIDQ4738141zbMATH OpenFDO

Authors Ndedi Monekosso, Paolo Remagnino, Adam Szarowicz

Publication date 11 August 2004

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2296/22960197.htm

zbMATH Keywords

CommunicationCoordinationMachine LearningMulti-agentsPheromones

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99)

Recommendations

• Phe-Q: A pheromone based Q-learning
• An analysis of the pheromone Q-learning algorithm
• A new Q learning algorithm for multi-agent systems
• Learning sensitive stigmergic agents for solving complex problems
• Updating ACO pheromones using stochastic gradient ascent and cross-entropy methods

Cited in

(4)

• Implementing Pheromone-Based, Negotiating Forager Agents
• An analysis of the pheromone Q-learning algorithm
• Phe-Q: A pheromone based Q-learning
• DQL: A new updating strategy for reinforcement learning based on Q-learning

This page was built for publication: An improved Q-learning algorithm using synthetic pheromones

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4738141)