The MaxSolve algorithm for coevolution

• DOI: 10.1145/1068009.1068091
• Publication Date: 2005-08-03T08:31:47Z
• Authors: Edwin de Jong
• Keywords: Coevolution

Coevolution can be used to adaptively choose the tests for evaluating candidate solutions. A long-standing question is how this dynamic setup may organized yield reliable search methods. Reliability only considered in connection with a particular solution concept specifying what constitutes solution. Recently, monotonic coevolution algorithms have been proposed several concepts. Here, we introduce new algorithm that guarantees monotonicity of maximizing expected utility The method, called MaxSolve, compared IPCA and found perform more efficiently range parameter values on an abstract test problem.