INFLUENCE LEARNING FOR MULTI-AGENT SYSTEM BASED ON REINFORCEMENT LEARNING
DOI:
https://doi.org/10.47839/ijc.11.1.549Keywords:
Reinforcement learning, influence learning, multi-agent learning, multi-joined robot.Abstract
This paper describes a multi-agent influence learning approach and reinforcement learning adaptation to it. This learning technique is used for distributed, adaptive and self-organizing control in multi-agent system. This technique is quite simple and uses agent’s influences to estimate learning error between them. The best influences are rewarded via reinforcement learning which is a well-proven learning technique. It is shown that this learning rule supports positive-reward interactions between agents and does not require any additional information than standard reinforcement learning algorithm. This technique produces optimal behavior of multi-agent system with fast convergence patterns.References
Vidal H.M., Fundamentals of Multiagent Systems with Net Logo Examples, E-book: www.multiagent.com, (2008).
Panait L. and Luke S., Cooperative multi-agent learning: the state of the art, Autonomous Agents and Multi-Agent Systems, (11) 3 (2005), pp. 387-434.
Alonso E., D’Inverno M., Kudenko D., Luck M., Noble J., Learning in Multi-Agent Systems. Science Report, Discussion. UK’s Special Interest Group on Multi-Agent Systems, (2001).
Gabel T., Multi-Agent Reinforcement Learning Approaches for Distributed Job-Shop Scheduling Problems, PhD Thesis, University of Osnabrueck, 2009.
Bab A., Brafman R.I., Multi-agent reinfor-cement learning in common interest and fixed sum stochastic games: an experimental study, Journal of Machine Learning Research, (9) (2008), pp. 2635-2675.
Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press., (1998).
Worgotter F., Porr B., Temporal sequence learning, prediction and control – A review of different models and their relation to biological mechanisms, Neural Computation, (17) (2005), pp. 245-319.
Tan Ming, Multiagent reinforcement learning. Independent vs cooperative agents, Autonomous Agents and Multiagent Systems, (10) 3 (2005), pp. 273-328.
Shoham Y., Powers R., Grenager T., If multi-agent learning is the answer, what is the question, Journal of Artificial Intelligence, (2006).
Stone P., Multiagent learning is not the answer. It is a question, Artificial Intelligence, (171) (2007), pp. 402-405.
Kabysh A., Golovko V., Mikhniayeu A., Lipnickas A., Behaviour patterns of adaptive multi-joined robot learned by multi-agent influence reinforcement learning, Proceedings of Pattern Recognition and Image Processing (PRIP–2011), 2011, 19–21 May, BSU, Minsk, pp. 392-297.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
