Vidal's library
Title: Using Landscape Theory to Measure Learning Difficulty for Adaptive Agents
Author: Christopher H. Brooks and Edmund H. Durfee
Book Tittle: Adaptive Agents and Multi-Agent Systems
Publisher: Lecture Notes in Artificial Intelligence, Springer-Verlag
Year: 2003
Abstract: We compare the usefullness of three different metrics for estimating ruggedness on learning problems in an information economy domain.We empirically evaluate the ability of each metric to predict ruggedness and use these metrics to explain past results showing that problems that yield equal reward when completely learned yield different profits to an adaptive learning agent.

Cited by 1  -  Google Scholar

@InCollection{brooks03a,
  author =	 {Christopher H. Brooks and Edmund H. Durfee},
  title =	 {Using Landscape Theory to Measure Learning
                  Difficulty for Adaptive Agents},
  booktitle =	 {Adaptive Agents and Multi-Agent Systems},
  publisher =	 {Lecture Notes in Artificial Intelligence,
                  Springer-Verlag},
  year =	 2003,
  abstract =	 {We compare the usefullness of three different
                  metrics for estimating ruggedness on learning
                  problems in an information economy domain.We
                  empirically evaluate the ability of each metric to
                  predict ruggedness and use these metrics to explain
                  past results showing that problems that yield equal
                  reward when completely learned yield different
                  profits to an adaptive learning agent.},
  keywords =     {learning multiagent complexity},
  url =		 {http://jmvidal.cse.sc.edu/library/brooks03a.pdf},
  googleid = 	 {Vnz-gB7dZkoJ:scholar.google.com/},
  cluster = 	 {5361215529514073174}
}
Last modified: Wed Mar 9 10:16:02 EST 2011