Vidal's library
Title: Agents Learning about Agents: A Framework and Analysis
Author: José M. Vidal and Edmund H. Durfee
Book Tittle: Multiagent Learning Workshop
Year: 1997
Abstract: We provide a framework for the study of learning in certain types of multi-agent systems (MAS), that divides an agent's knowledge about others into different “types”. We use concepts from computational learning theory to calculate the relative sample complexities of learning the different types of knowledge, given either a supervised or a reinforcement learning algorithm. These results apply only for the learning of a fixed target function, which would probably not exist if the other agents are also learning. We then show how a changing target function affects the learning behaviors of the agents, and how to determine the advantages of having lower sample complexity. Our results can be used by a designer of a learning agent in a MAS to determine which knowledge he should put into the agent and which knowledge should be learned by the agent.

Cited by 35  -  Google Scholar

@InProceedings{   vidal:97a,
  author =	 {Jos\'{e} M. Vidal and Edmund H. Durfee},
  title =	 {Agents Learning about Agents: A Framework and
                  Analysis},
  booktitle =	 {Multiagent Learning Workshop},
  url =		 {http://jmvidal.cse.sc.edu/papers/lmas/},
  year =	 {1997},
  abstract =	 {We provide a framework for the study of learning in
                  certain types of multi-agent systems (MAS), that
                  divides an agent's knowledge about others into
                  different ``types''. We use concepts from
                  computational learning theory to calculate the
                  relative sample complexities of learning the
                  different types of knowledge, given either a
                  supervised or a reinforcement learning
                  algorithm. These results apply only for the learning
                  of a fixed target function, which would probably not
                  exist if the other agents are also learning. We then
                  show how a changing target function affects the
                  learning behaviors of the agents, and how to
                  determine the advantages of having lower sample
                  complexity. Our results can be used by a designer of
                  a learning agent in a MAS to determine which
                  knowledge he should put into the agent and which
                  knowledge should be learned by the agent. },
  googleid = 	 {WrPbNSW5P84J:scholar.google.com/},
  keywords = 	 {multiagent learning},
  cluster = 	 {14861800864814445402}
}
Last modified: Wed Mar 9 10:14:06 EST 2011