Reference and Bibtex for Coevolutionary free lunches by Wolpert, D. H. et. al.

@article{CoevolutionaryFreeLunches,
	author = {D. H. Wolpert and W. G. Macready},
	doi = {10.1109/TEVC.2005.856205},
	journal = {IEEE Transactions on Evolutionary Computation},
	month = {December},
	number = {6},
	pages = {721--735},
	title = {Coevolutionary free lunches},
	volume = {9},
	year = {2005}
}

Language:
  en
Type:
  article
Title:
  Coevolutionary free lunches
Author:
  Wolpert, D. H. et. al.
Topic:
  Science / Artificial Life / Evolutionary Algorithms
Rating:
  4
Comment:

"However, all this previous work has been cast in a manner that does not cover repeated game scenarios where the "objective function" for one player or agent can vary based on the response of another player. In particular, the NFL theorems do not cover such scenarios. These game-like scenarios are usually called "coevolutionary" since they involve the behaviors of more than a single agent or player."

"The NFL theorems concern averages over all f of quantities depending on C. For those theorems to hold in a GO scenario - for f-averages of C to be independent of the search algorithmÃ¢â‚¬â€it is crucial that for fixed d_m, C does not depend on f."

Acquired:
2006-02-24

Reference:

Bibtex:

Other information: