用对抗构造法高效发现人类行为新模式，突破大任务空间实验瓶颈。
Adversarial construction as a potential solution to the experiment design problem in large task spaces
- 构建对抗性任务，挖掘最可能引发新行为的极端案例。
- 相比随机采样，对抗构造在识别新行为上提升显著。
- 适合研究认知机制与复杂任务空间的学者参考。
尽管数十年的研究进展，我们仍缺乏对人类行为的通用理论，甚至在最简单领域亦然。本文直面这一普遍性难题，旨在建立一个覆盖整个任务空间的统一模型。具体聚焦于二进制序列预测任务，其观测数据由隐马尔可夫模型（HMM）参数化生成。由于任务空间庞大，全面实验探索不可行。为此，我们提出对抗构造方法，用于识别最可能诱发定性新行为的任务。结果表明，该方法显著优于随机环境采样，有望作为高维任务空间中最优实验设计的代理方案。
原文摘要 · Abstract (English)
Despite decades of work, we still lack a robust, task-general theory of human behavior even in the simplest domains. In this paper we tackle the generality problem head-on, by aiming to develop a unified model for all tasks embedded in a task-space. In particular we consider the space of binary sequence prediction tasks where the observations are generated by the space parameterized by hidden Markov models (HMM). As the space of tasks is large, experimental exploration of the entire space is infeasible. To solve this problem we propose the adversarial construction approach, which helps identify tasks that are most likely to elicit a qualitatively novel behavior. Our results suggest that adversarial construction significantly outperforms random sampling of environments and therefore could be used as a proxy for optimal experimental design in high-dimensional task spaces.
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。