1
Optimizing Regret
计量经济学前沿论文，探讨如何系统性地优化决策中的遗憾值问题。
arXiv:2607.18866v1 Announce Type: cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, thi…
2
Generalised Bellman recurrence and three dualities in sequential decision-making
全新广义贝尔曼递推揭示序列决策中的三重对偶性，重塑强化学习与最优控制理论基础。
arXiv:2607.18077v1 Announce Type: cross Abstract: What gives the Bellman equation its form? We show that the recursive properties of optimal value fun…
3
Internal Pluralism and the Limits of Pairwise Comparisons
当多元价值并存，成对比较为何失效？一篇挑战决策底层逻辑的硬核论文，值得深读。
arXiv:2607.02672v1 Announce Type: new Abstract: Local pairwise comparisons are a standard tool for learning how people want decision rules to work, e.…
4
Learning to Decide with AI Assistance under Human-Alignment
前沿研究探讨如何让AI助手在符合人类偏好的前提下辅助决策，揭秘人机对齐新方法
arXiv:2605.12646v2 Announce Type: replace-cross Abstract: It is widely agreed that when AI models assist decision-makers in high-stakes domains by pre…
5
Evaluating AI Investment Strategies
从输入输出审计黑箱算法，动态政策遗憾可分解为协方差之和，理论透彻。
arXiv:2606.08791v1 Announce Type: cross Abstract: We study the problem of auditing a black-box algorithmic decision-maker from observable inputs and o…
6
Statistical Decision Theory with Counterfactual Loss
探讨统计决策理论中引入反事实损失的新框架，为因果推断与机器学习决策提供理论支撑。
arXiv:2505.08908v3 Announce Type: replace-cross Abstract: Many researchers apply classical statistical decision theory to evaluate treatment choices a…
7
Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors
贝叶斯模型平均在决策树上的样本复杂度与决策理论保证，Catalan-Exponential先验的新进展。
arXiv:2606.01340v1 Announce Type: new Abstract: We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic …
8
MINTS: Minimalist Thompson Sampling
提出极简主义的Thompson采样方法MINTS，用最少的假设实现高效决策，贝叶斯优化领域的新思路。
arXiv:2606.01655v1 Announce Type: cross Abstract: The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but …
9
Scaling Observation-aware Planning in Uncertain Domains
提出在不确定性领域内扩展观测感知规划的新方法，为复杂环境决策提供可扩展方案。
arXiv:2605.22364v1 Announce Type: new Abstract: Deciding which sensing capabilities to deploy on an agent in uncertain domains is a fundamental engine…