Understanding how evolutionary agents behave in complex environments is a challenging problem. Agents can be faced with complex fitness landscapes derived from multi-stage tasks, interaction with others, and limited environmental feedback. Agents that evolve to overcome these can sometimes access greater fitness, as a result of factors such as cooperation and tool use. However, it is often difficult to explain why evolutionary agents behave in certain ways, and what specific elements of the environment or task may influence the ability of evolution to find goal-achieving behaviours; even seemingly simple environments or tasks may contain features that affect agent evolution in unexpected ways. We explore principled simplification of evolutionary agent-based models, as a possible route to aiding their explainability. Using the River Crossing Task (RCT) as a case study, we draw on analysis in the Minimal River Crossing (RC-) Task testbed, which was designed to simplify the original task while keeping its key features. Using this method, we present new analysis concerning when agents evolve to successfully complete the RCT. We demonstrate that the RC- environment can be used to understand the effect that a cost to movement has on agent evolution, and that these findings can be generalised back to the original RCT. Then, we present new insight into the use of principled simplification in understanding evolutionary agents. We find evidence that behaviour dependent on features that survive simplification, such as problem structure, are amenable to prediction; while predicting behaviour dependent on features that are typically reduced in simplification, such as scale, can be invalid.

中文翻译：

---

通过原则简化解释基于进化代理的模型。


了解进化代理在复杂环境中的行为是一个具有挑战性的问题。智能体可能面临来自多阶段任务、与他人交互和有限环境反馈的复杂适应度景观。由于合作和工具使用等因素，为克服这些问题而进化的智能体有时可以获得更大的适应性。然而，通常很难解释为什么进化主体以某些方式表现，以及环境或任务的哪些特定元素可能会影响进化找到实现目标的行为的能力；即使看似简单的环境或任务也可能包含以意想不到的方式影响代理进化的功能。我们探索基于进化代理的模型的原则简化，作为帮助其可解释性的可能途径。我们以过河任务（RCT）作为案例研究，借鉴了最小过河任务（RC-）测试平台的分析，该测试平台旨在简化原始任务，同时保留其关键特征。使用这种方法，我们提出了关于智能体何时进化以成功完成 RCT 的新分析。我们证明，RC 环境可用于理解运动成本对智能体进化的影响，并且这些发现可以推广回原始 RCT。然后，我们提出了在理解进化主体时使用原则简化的新见解。我们发现证据表明，依赖于简化后的特征（例如问题结构）的行为是可以预测的。而预测依赖于通常在简化过程中减少的特征（例如规模）的行为可能是无效的。