AI 中文总结
本研究通过对比直接、静态生成和发育编码，发现发育编码虽增加表型多样性但降低局部性与重组稳健性，主张以多维度几何而非单一性能评估发育编码。
AI 中文摘要
发育编码通常源于一种期望，即结构化的基因型到表型过程能够改善可进化性、稳健性和适应性。然而，一种扩大表型变异的编码可能同时使有用的亲本结构在突变和重组下更难保持。我们在一个受控的进化机器人基准测试中检验了这一权衡，比较了三种匹配的表示：直接编码、静态生成编码和时间合子发育编码。所有三种条件均使用34个基因组参数、34个成年控制器参数、相同的初始基因组矩阵、相同的优化器、相同的突变和交叉算子、相同的环境以及相同数量的适应度评估。每种表示进行30次配对进化运行，发育编码在最终训练适应度或分布外适应度上并未可靠地超过直接编码。然而，它确实显著增加了最终种群表型多样性和突变可达的表型多样性。同一表示表现出较低的突变存活率、较低的基因型-表型局部性、急剧降低的交叉后代适应度和存活率，以及增加的重组新颖性。持续的发育动态还减弱了在发育早期施加的损伤，相对于其他方面相同的晚期损伤。这些结果识别出一个表示层面的权衡：发育可以扩大可达表型的邻域并提供发育内的损伤衰减，同时削弱已适应结构的局部遗传。我们认为，发育编码因此不应仅通过性能来评估，而应通过生成性、局部性、稳健性和遗传兼容性的联合几何来评估。
英文摘要
Developmental encodings are often motivated by the expectation that a structured genotype-to-phenotype process can improve evolvability, robustness, and adaptation. Yet an encoding that expands phenotypic variation may simultaneously make useful parental structure harder to preserve under mutation and recombination. We test this trade-off in a controlled evolutionary-robotics benchmark comparing three matched representations: direct encoding, a static generative encoding, and a temporal zygotic developmental encoding. All three conditions use 34 genome parameters, 34 adult-controller parameters, identical initial genome matrices, the same optimizer, the same mutation and crossover operators, the same environments, and the same number of fitness evaluations. Across 30 paired evolutionary runs per representation, developmental encoding does not reliably exceed direct encoding in final training or out-of-distribution fitness. It does, however, substantially increase final population phenotypic diversity and mutant-reachable phenotype diversity. The same representation exhibits lower mutation viability, lower genotype--phenotype locality, sharply reduced crossover offspring fitness and viability, and increased recombination novelty. Continued developmental dynamics also attenuate damage applied early in development relative to otherwise identical late damage. These results identify a representation-level trade-off: development can enlarge the neighborhood of reachable phenotypes and provide within-development damage attenuation while degrading the local inheritance of already-adapted structure. We argue that developmental encodings should therefore be evaluated not by performance alone, but by a joint geometry of generativity, locality, robustness, and inheritance compatibility.
