arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01066cs.SIcs.AIcs.MAcs.SYeess.SY
收藏

集体智能的主动推理模型

An active inference model of collective intelligence

Carnegie Mellon University(卡内基梅隆大学);University of Oxford(牛津大学);Australian National University(澳大利亚国立大学)

Rafael Kaufmann, Pranav Gupta, Jacob Taylor

摘要:

到目前为止,集体智慧的正式模型缺乏一个合理的数学描述之间的关系高度自治的子系统组件(个人)和复合系统(集体)的全球规模的行为之间的局部规模的相互作用。在本文中,我们使用的主动推理公式(AIF),一个框架,用于解释任何非平衡稳态系统在任何规模的行为,以建立一个最小的基于代理的模型,模拟本地个人层面的互动和集体智慧(操作系统级的性能)之间的关系。我们探讨了提供具有特定认知能力的基线AIF代理(模型1)的影响:心理理论(模型2);目标对齐(模型3)和具有目标对齐的心理理论(模型4)。认知能力复杂性的这些逐步转变是由AIF代理在由其他AIF代理填充的环境中持续和蓬勃发展所必需的进步类型所激发的,并且最近也被证明自然映射到人类认知能力的典型步骤。说明性的结果表明,逐步认知过渡,提高系统性能,提供互补的机制,代理的局部和全局最优之间的对齐。对齐从相互作用的AIF代理本身的动态中内生地出现,而不是通过对代理行为的激励(与现有的集体智能的计算模型相反)或集体行为的自上而下的先验(与现有的AIF多尺度模拟相反)来外源地施加。这些结果揭示了有利于人类和其他复杂适应系统中集体智慧的通用信息理论模式的类型。

英文摘要:

To date, formal models of collective intelligence have lacked a plausible mathematical description of the relationship between local-scale interactions between highly autonomous sub-system components (individuals) and global-scale behavior of the composite system (the collective). In this paper we use the Active Inference Formulation (AIF), a framework for explaining the behavior of any non-equilibrium steady state system at any scale, to posit a minimal agent-based model that simulates the relationship between local individual-level interaction and collective intelligence (operationalized as system-level performance). We explore the effects of providing baseline AIF agents (Model 1) with specific cognitive capabilities: Theory of Mind (Model 2); Goal Alignment (Model 3), and Theory of Mind with Goal Alignment (Model 4). These stepwise transitions in sophistication of cognitive ability are motivated by the types of advancements plausibly required for an AIF agent to persist and flourish in an environment populated by other AIF agents, and have also recently been shown to map naturally to canonical steps in human cognitive ability. Illustrative results show that stepwise cognitive transitions increase system performance by providing complementary mechanisms for alignment between agents' local and global optima. Alignment emerges endogenously from the dynamics of interacting AIF agents themselves, rather than being imposed exogenously by incentives to agents' behaviors (contra existing computational models of collective intelligence) or top-down priors for collective behavior (contra existing multiscale simulations of AIF). These results shed light on the types of generic information-theoretic patterns conducive to collective intelligence in human and other complex adaptive systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑