Self-organizing neural architectures and multi-agent cooperative reinforcement learning
Dan Xiao · 2010
Multi-agent system, wherein multiple agents work to perform tasks jointly through their interaction, is a fairly well studied problem.Many approaches to multi-agent learning exist, among which, reinforcement learning is widely used, as it does not require an explicit model of the environment.However, limitations remain in current multi-agent reinforcement learning approaches, including adaptability and scalability in complex and specialized multi-agent domains.In any multi-agent reinforcement learning system, two major consid-I am really grateful to my supervisor, Dr. Tan Ah Hwee, for his patient guidance and invaluable advices for this thesis and all that I've achieved so far.I would also like to acknowledge the support from my family members, especially my wife, my father and my father-in-law, who stand firmly behind me all the time.This work is also a precious gift for my growing daughter.