Comparing tree depth limits and resource-limited GP

摘要: In this paper we compare two different approaches for controlling bloat in genetic programming, tree depth limits and resource-limited GP. Tree operate at the individual level, avoiding excessive code growth by imposing a maximum to each individual. Resource-limited GP is new technique that operates population limiting total amount of resources entire can use. We their dynamics performance on three problems: symbolic regression, even parity, artificial ant. The results suggest superior limits, but question superiority discuss possible ways combining strengths both approaches, further improve