On-policy concurrent reinforcement learning

DOI10.1080/09528130412331297956zbMATH Open1066.68106OpenAlexW1972847450WikidataQ113437934 ScholiaQ113437934MaRDI QIDQ4670596FDOQ4670596

Authors: Bikramjit Banerjee, Sandip Sen, Jing Peng 

Publication date: 22 April 2005

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

Full work available at URL: https://doi.org/10.1080/09528130412331297956

Recommendations

• Multiagent learning using a variable learning rate
• A new \(Q\) learning algorithm for multi-agent systems
• AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
• scientific article; zbMATH DE number 5957383
• Individual Q-Learning in Normal Form Games

zbMATH Keywords

multi-agent learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Theory of software (68N99)

Cites Work

• Non-cooperative games
• \({\mathcal Q}\)-learning
• Multiagent learning using a variable learning rate
• An analysis of temporal-difference learning with function approximation
• Two-person nonzero-sum games and quadratic programming
• Convergence results for single-step on-policy reinforcement-learning algorithms
• Fast online \(Q(\lambda)\)

Cited In (1)

• Concurrent Q-learning: Reinforcement learning for dynamic goals and environments

This page was built for publication: On-policy concurrent reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4670596)