MPI for Software Systems（软件系统马克斯·普朗克研究所）；Reasonal, Inc.（Reasonal公司）；Monash University（莫纳什大学）；MPI for Intelligent Systems（智能系统马克斯·普朗克研究所）
Stratis Tsirtsis, Behzad Tabibian, Moein Khajehnejad, Adish Singla, Bernhard Schölkopf, Manuel Gomez-Rodriguez
备注：
New method of estimating the outcome probabilities and setting the cost function values. New experiments on credit card data. Performance optimization in the presence of non-actionable features
We are witnessing an increasing use of data-driven predictive models to inform decisions. As decisions have implications for individuals and society, there is increasing pressure on decision makers to be transparent about their decision policies. At the same time, individuals may use knowledge, gained by transparency, to invest effort strategically in order to maximize their chances of receiving a beneficial decision. Our goal is to find decision policies that are optimal in terms of utility in such a strategic setting. To this end, we first characterize how strategic investment of effort by individuals leads to a change in the feature distribution. Using this characterization, we first show that, in general, we cannot expect to find optimal decision policies in polynomial time and there are cases in which deterministic policies are suboptimal. Then, we demonstrate that, if the cost individuals pay to change their features satisfies a natural monotonicity assumption, we can narrow down the search for the optimal policy to a particular family of decision policies with a set of desirable properties, which allow for a highly effective polynomial time heuristic search algorithm using dynamic programming. Finally, under no assumptions on the cost individuals pay to change their features, we develop an iterative search algorithm that is guaranteed to find locally optimal decision policies also in polynomial time. Experiments on synthetic and real credit card data illustrate our theoretical findings and show that the decision policies found by our algorithms achieve higher utility than those that do not account for strategic behavior.
Solvay Business School（索尔维商学院）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；Antwerp Management School（安特卫普管理学院）；Universiteit Antwerpen（安特卫普大学）；Faculty of Business and Economics（商业与经济学院）；Katholieke Universiteit Leuven（鲁汶大学）
The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
School of Computer Science, Peking University（北京大学计算机科学学院）；Center for Data Science, Peking University（北京大学数据科学中心）；National Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（北京大学通用人工智能国家重点实验室）；Northwestern University（西北大学）；Yale University（耶鲁大学）
The impact of machine learning forecasting on strategic decision-making for Bike Sharing Systems
Department of Economics and Management University of Brescia（经济学与管理学院布雷西亚大学）；Department of Management, Economics and Industrial Engineering Politecnico di Milano（管理、经济与工业工程学院米兰理工学院）
DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（人工智能学院，中国科学院大学，北京，中国）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院，北京，中国）
Explaining Strategic Decisions in Multi-Agent Reinforcement Learning for Aerial Combat Tactics
Dalle Molle Institute for Artificial Intelligence (IDSIA) - SUPSI/USI（达勒莫尔人工智能研究所（IDSIA）- 瑞士南部应用科学与艺术大学/瑞士意大利语区大学）；armasuisse Science and Technology（瑞士联邦国防采购局科学与技术）
Online Markov Decision Processes with Non-oblivious Strategic Adversary
University of Southampton（南安普顿大学）；Huawei R&D UK（华为英国研发中心）；University of Warwick（华威大学）；University College London（伦敦大学学院）
我们研究了在线马尔可夫决策过程（OMDPs）中的一个新的设置，其中的损失函数是由一个非遗忘的战略对手谁遵循无外部遗憾算法选择。在这种情况下，我们首先证明了MDP-Expert，一个现有的算法，可以很好地与不经意的对手仍然可以应用和实现的政策遗憾界的$\mathcal{O}(\sqrt{T \log(L)}+τ^2\sqrt{ T \log(|A|)})$其中$L$是对手的纯策略集的大小和$|A|$表示代理的动作空间的大小。考虑到现实世界的游戏中，一个NE的支持大小是小的，我们进一步提出了一个新的算法：MDP-OOE在线Oracle专家（MDP-OOE），实现了$\mathcal{O}(\sqrt{T\log(L)}+τ^2\sqrt{ T k \log(k)})$的政策遗憾界，其中$k$只依赖于支持大小的NE。MDP-OOE在博弈论中利用了双预言的关键优势，因此可以解决具有过大动作空间的游戏。最后，为了更好地理解无遗憾方法的学习动态，在OMDPs中的无外部遗憾对手的相同设置下，我们引入了一种算法，该算法实现了NE的最后一轮收敛结果。据我们所知，这是第一个工作，导致OMDPs的最后一次迭代结果。
Predicting Stock Prices using Permutation Decision Trees and Strategic Trailing
Department of Computer Science and Information Systems（计算机科学与信息系统系）；BITS Pilani K K Birla Goa Campus（比斯潘大学KK比拉戈阿校区）；Complex Systems Programme（复杂系统计划）；National Institute of Advanced Studies, IISc Campus（国家先进研究院，IISc校区）；Consciousness Studies Programme（意识研究计划）
本文提出基于 Permutation Decision Trees 和 strategic trailing 的高频交易策略，在印度股市等数据上测试，其利润达1.1802%，优于LSTM、RNN及买入并持有策略。
Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic Agents
National University of Defense Technology, Changsha, China（国防科技大学）；Peking University, Beijing, China（北京大学）；Shanghai University of Finance and Economics, Shanghai, China（上海财经大学）；ZGC Laboratory, Beijing, China（ZGC实验室）；Faculty of Computing, Harbin Institute of Technology, Harbin, China（哈尔滨工业大学计算机学院）
