人工智能中的信息论度量：实用决策指南
Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and Remedies
AI总结：
本文为七种信息论度量提供实用决策框架，围绕每个度量的三个关键问题：回答的问题与AI场景、适合的估计器、最危险的误用，并附有流程图和决策表。
摘要：
信息论（IT）度量在人工智能中无处不在：熵驱动决策树分裂和不确定性量化，交叉熵是默认的分类损失，互信息支撑表示学习和特征选择，转移熵揭示动态系统中的有向影响。第二类较不成熟的度量——整合信息（Phi）、有效信息（EI）和自主性——已出现用于表征智能体复杂性。尽管被广泛采用，度量选择常常与估计器假设、失败模式和安全的推断主张脱节。本文为所有七种度量提供了一个实用决策框架，围绕每个度量的三个指导性问题组织：（i）该度量回答什么问题，在何种AI背景下；（ii）哪种估计器适合数据类型和维度；（iii）最危险的误用是什么。该框架通过两个互补的人工制品实现：度量选择流程图和主决策表。我们涵盖每个度量的AI/ML和决策智能体应用领域，并使用标准化桥接框将IT量与认知构造联系起来。三个工作示例展示了该框架在具体从业者场景中的应用，涵盖表示学习、时间影响分析和进化智能体复杂性。
英文摘要：
Reporting guidance for information-theoretic measures is rarely tested against ground truth. We test one guardrail in two multi-agent reinforcement learning games, a social dilemma and a coordination race, where directed influence between selected agent pairs is zero by construction, over 100 seeds. Omitting one precondition, exclusion of the non-stationary training transient, gives false-positive rates of 100.00% and 99.95%: agents annealing exploration independently, in runs that never met, are flagged as influencing one another. Excluding the transient reaches 3.05% in the social dilemma but 11.8% in the coordination game, so the non-stationarity must be treated and exclusion is neither the only way nor sufficient. What we recommend instead changes the null model. Series, statistic and estimand are left untouched: permuting the source within blocks of training time reaches 5.25% and 5.50%, the only one of the three at or below the size of the test in both games. The construction is not new, being a restricted permutation local to blocks of training time; the measurement is. A third null control, four learners in the social dilemma, defeats all three, and there conditioning costs three times what ours does, 15.20 points against 4.55. Titrating injected links separates it from conditioning on identical pairs, 82.5% against 58.0%, while the ablated test reports a positive with or without a link, so its apparent sensitivity is uninformative. Five block counts spanning 16 to 256 land in the nominal region. Code and data are released.
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。
