Sciweavers

GECCO
2008
Springer

How generative encodings fare on less regular problems

13 years 4 months ago
How generative encodings fare on less regular problems
Generative representations allow the reuse of code and thus facilitate the evolution of repeated phenotypic themes or modules. It has been shown that generative representations perform well on highly regular problems. To date, however, generative representations have not been tested on irregular problems. It is unknown how fast their performance degrades as the regularity of the problem decreases. In this report, we test a generative representation on a problem where we can scale a type of regularity in the problem. The generative representation outperforms a direct encoding control when the regularity of the problem is high but degrades to, and then underperforms, the direct control as the regularity of the problem decreases. Importantly, this decrease is not linear. The boost provided by the generative encoding is only significant for very high levels of regularity. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Connectionism and Neural Nets General Terms Experi...
Jeff Clune, Charles Ofria, Robert T. Pennock
Added 09 Nov 2010
Updated 09 Nov 2010
Type Conference
Year 2008
Where GECCO
Authors Jeff Clune, Charles Ofria, Robert T. Pennock
Comments (0)