对比三种神经进化策略在复杂生态中的表现差异。
Neuroevolution Arena: Nested Ecological Evaluation of Update-and-Inheritance Regimes across Neural Architectures
- 设计多场景生态评估框架，分离训练与评估变量。
- 三种策略中强化学习类方法训练表现更优，但生态适应性各异。
- 结果高度依赖具体模型与环境设定，适合研究算法鲁棒性者参考。
竞争性人工生命系统在训练与生态评估中可能对控制器排名产生不同结果。本文提出Neuroevolution Arena，一个基于GPU加速的独立参数化神经网络单元空间生态模拟系统，以及可追溯的嵌套评估协议。三种特定实现的更新与继承机制（EvoEvo、EvoRL、RLRL）与两种神经架构组合，在每种条件下进行三轮独立训练，共50,000代。每轮18次运行各保存一个精英控制器，进入对齐运行冻结评估，共198个计算任务。每个对齐训练块内平均三个种子定义的生态情境（两个允许多体合作，一个允许攻击），独立水平保持n=3运行每条件。结果显示，含强化学习的机制在训练适应度上高于EvoEvo，但成对结果呈现架构依赖的多数模式和显著的个体依赖性。六类胜出者在不同个体与情境间变化，预设生存终点出现完全失效。我们贡献了一种嵌套协议，将训练产物与评估情境分离，暴露而非掩盖其变异来源。
原文摘要 · Abstract (English)
Competitive artificial-life systems can rank trained controllers differently under training and ecological evaluation. We present Neuroevolution Arena, a GPU-accelerated spatial ecology of independently parameterized neural-network cells, and an audit-tracked nested evaluation protocol. Three implementation-specific update-and-inheritance regimes (EvoEvo, EvoRL, and RLRL) are crossed with two neural architectures for 50,000 generations in three independent training runs per condition. One saved elite-controller artifact from each of the 18 runs enters an aligned-run frozen-evaluation design comprising 198 computational jobs. Pairwise effects average three seed-defined ecological contexts (two cooperation-permitting and one attack-permitting) within each aligned training-run block; the independent level remains n = 3 runs per condition. RL-enabled regimes attain higher recorded training fitness than EvoEvo, whereas pairwise outcomes show architecture-conditioned majority patterns and substantial artifact dependence. Six-way winners vary across artifacts and contexts, and the prespecified survival endpoint has a complete floor. We contribute a nested protocol that separates training-run artifacts from evaluation contexts and exposes, rather than conceals, their different sources of variation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。