Artificial Intelligence最新文献_第6页

Social behavior as a key to learning-based multi-agent pathfinding dilemmas 社会行为是基于学习的多智能体寻径困境的关键

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-30 DOI: 10.1016/j.artint.2025.104397

Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti

The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: marmotlab.github.io/mapf_sylph.

多代理寻路（Multi-agent Path Finding， MAPF）问题涉及在已知的静态环境中为一组代理寻找无冲突的路径，在仓库自动化、物流或最后一英里交付中具有重要应用。为了满足这些大规模应用程序的需求，当前基于学习的方法通常为所有代理部署相同的经过充分训练的分散网络，以提高可扩展性。然而，这种参数共享通常会导致代理之间的同质行为，这可能会阻止代理打破围绕对称冲突（例如，瓶颈）的联系，并可能导致活锁/死锁。在本文中，我们提出了SYLPH，这是一种新的基于学习的MAPF框架，旨在通过允许智能体学习和动态选择不同的社会行为（类似于个体的动态角色），而不影响参数共享提供的可扩展性，从而减轻同质性的不利影响。具体而言，SYLPH通过引入社会价值取向（SVO）作为一个在政策制定和奖励分配中发挥核心作用的时间扩展潜在变量，提供了一种新的分层机制。为了支持这种分层决策过程，我们引入了社会感知多策略PPO (smp30)，这是一种强化学习方法，通过交叉利用优势的机制确保稳定有效的训练。此外，我们设计了一种基于svo的学习断绳算法，允许智能体主动避免碰撞，而不是仅仅依赖后处理技术。由于这种分层决策和社会偏好的交换，SYLPH赋予智能体通过更多潜在空间和微妙背景来推理MAPF任务的能力，从而导致不同的反应，有助于打破对称冲突周围的联系。我们的对比实验表明，SYLPH达到了最先进的性能，在随机、房间和迷宫地图中超越了其他基于学习的MAPF规划器，而我们的消融研究表明了SYLPH中每个组件的优势。最后，我们在三种类型的地图上通过实验验证了我们在硬件上训练好的策略，展示了SYLPH如何允许智能体在现实条件下找到高质量的路径。我们的代码和视频可在：marmotlab.github.io/mapf_sylph。

{"title":"Social behavior as a key to learning-based multi-agent pathfinding dilemmas","authors":"Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti","doi":"10.1016/j.artint.2025.104397","DOIUrl":"10.1016/j.artint.2025.104397","url":null,"abstract":"<div><div>The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: <span><span>marmotlab.github.io/mapf_sylph</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104397"},"PeriodicalIF":4.6,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MATE: Masked optimal transport with dynamic selection for partial label graph learning 部分标签图学习的动态选择掩膜最优传输

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-29 DOI: 10.1016/j.artint.2025.104396

Yiyang Gu , Binqi Chen , Zihao Chen , Ziyue Qiao , Xiao Luo , Junyu Luo , Zhiping Xiao , Wei Ju , Ming Zhang

This paper investigates the problem of partial label graph learning, in which every graph is associated with a set of candidate labels. Previous methods for weakly supervised graph classification often provide pseudo-labels for graph samples that could be overconfident and biased towards the dominant classes, thus resulting in substantial error accumulation. In this paper, we introduce a new framework named Masked Optimal Transport with Dynamic Selection (MATE) for partial label graph learning, which improves the quality of graph assignments from the perspectives of class balancing and uncertainty mining. In particular, our MATE masks probabilities out of candidate sets and then adopts optimal transport to optimize the assignments without class biases. This design is based on the assumption that the true label distribution is class-balanced or nearly balanced, which is common in various training datasets and real-world scenarios. To further reduce potential noise, we propose a novel scoring metric termed partial energy discrepancy (PED) to evaluate the uncertainty of assignments, and then introduce a dynamic selection strategy that modifies the sample-specific thresholds via momentum updating. Finally, these samples are divided into three levels, i.e., confident, less-confident, and unconfident and each group is trained separately in our collaborative optimization framework. Extensive experiments on various benchmarks demonstrate the superiority of our MATE compared to various state-of-the-art baselines.

本文研究了部分标签图学习问题，其中每个图都与一组候选标签相关联。以前的弱监督图分类方法通常为图样本提供伪标签，这些伪标签可能过于自信，并偏向于优势类，从而导致大量的误差积累。本文从类平衡和不确定性挖掘的角度，提出了一种新的局部标签图学习框架——动态选择掩膜最优传输（mask Optimal Transport with Dynamic Selection， MATE），提高了图分配的质量。特别地，我们的MATE屏蔽了候选集之外的概率，然后采用最优传输来优化没有类偏差的分配。这种设计基于真实标签分布是类平衡或接近平衡的假设，这在各种训练数据集和现实场景中很常见。为了进一步降低潜在的噪声，我们提出了一种新的评分指标，称为部分能量差异（PED）来评估分配的不确定性，然后引入了一种动态选择策略，通过动量更新来修改样本特定阈值。最后，将这些样本分为三个层次，即自信、不自信和不自信，并在我们的协同优化框架中单独训练每一组。在各种基准上进行的大量实验表明，与各种最先进的基线相比，我们的MATE具有优势。

{"title":"MATE: Masked optimal transport with dynamic selection for partial label graph learning","authors":"Yiyang Gu , Binqi Chen , Zihao Chen , Ziyue Qiao , Xiao Luo , Junyu Luo , Zhiping Xiao , Wei Ju , Ming Zhang","doi":"10.1016/j.artint.2025.104396","DOIUrl":"10.1016/j.artint.2025.104396","url":null,"abstract":"<div><div>This paper investigates the problem of partial label graph learning, in which every graph is associated with a set of candidate labels. Previous methods for weakly supervised graph classification often provide pseudo-labels for graph samples that could be overconfident and biased towards the dominant classes, thus resulting in substantial error accumulation. In this paper, we introduce a new framework named <u>M</u>asked Optim<u>a</u>l <u>T</u>ransport with Dynamic S<u>e</u>lection (MATE) for partial label graph learning, which improves the quality of graph assignments from the perspectives of class balancing and uncertainty mining. In particular, our MATE masks probabilities out of candidate sets and then adopts optimal transport to optimize the assignments without class biases. This design is based on the assumption that the true label distribution is class-balanced or nearly balanced, which is common in various training datasets and real-world scenarios. To further reduce potential noise, we propose a novel scoring metric termed partial energy discrepancy (PED) to evaluate the uncertainty of assignments, and then introduce a dynamic selection strategy that modifies the sample-specific thresholds via momentum updating. Finally, these samples are divided into three levels, i.e., confident, less-confident, and unconfident and each group is trained separately in our collaborative optimization framework. Extensive experiments on various benchmarks demonstrate the superiority of our MATE compared to various state-of-the-art baselines.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104396"},"PeriodicalIF":4.6,"publicationDate":"2025-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144810516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Interpreting capsule networks for image classification by routing path visualization 基于路由路径可视化的图像分类胶囊网络解释

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-17 DOI: 10.1016/j.artint.2025.104395

Amanjot Bhullar , Michael Czomko , R. Ayesha Ali , Douglas L. Welch

Artificial neural networks are popular for computer vision as they often give state-of-the-art performance, but are difficult to interpret because of their complexity. This black box modeling is especially troubling when the application concerns human well-being such as in medical image analysis or autonomous driving. In this work, we propose a technique called routing path visualization for capsule networks, which reveals how much of each region in an image is routed to each capsule. In turn, this technique can be used to interpret the entity that a given capsule detects, and speculate how the network makes a prediction. We demonstrate our new visualization technique on several real world datasets. Experimental results suggest that routing path visualization can precisely localize the predicted class from an image, even though the capsule networks are trained using just images and their respective class labels, without additional information defining the location of the class in the image.

人工神经网络在计算机视觉领域很受欢迎，因为它们通常提供最先进的性能，但由于其复杂性而难以解释。当医疗图像分析或自动驾驶等涉及人类福祉的应用程序时，这种黑盒建模尤其令人不安。在这项工作中，我们提出了一种称为胶囊网络路由路径可视化的技术，它揭示了图像中每个区域路由到每个胶囊的数量。反过来，这种技术可以用来解释给定胶囊检测到的实体，并推测网络如何做出预测。我们在几个真实世界的数据集上演示了我们新的可视化技术。实验结果表明，路由路径可视化可以精确地从图像中定位预测的类别，即使胶囊网络仅使用图像及其各自的类别标签进行训练，而没有额外的信息来定义图像中类别的位置。

引用次数: 0

Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning 多智能体强化学习中可证明的高效信息导向采样算法

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-10 DOI: 10.1016/j.artint.2025.104392

Qiaosheng Zhang , Chenjia Bai , Shuyue Hu , Zhen Wang , Xuelong Li

This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS). These algorithms draw inspiration from foundational concepts in information theory, and are proven to be sample efficient in MARL settings such as two-player zero-sum Markov games (MGs) and multi-player general-sum MGs. For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium. The basic algorithm, referred to as MAIDS, employs an asymmetric learning structure where the max-player first solves a minimax optimization problem based on the joint information ratio of the joint policy, and the min-player then minimizes the marginal information ratio with the max-player's policy fixed. Theoretical analyses show that it achieves a Bayesian regret of

\tilde{O} (\sqrt{K})

for K episodes. To reduce the computational load of MAIDS, we develop an improved algorithm called Reg-MAIDS, which has the same Bayesian regret bound while enjoying less computational complexity. Moreover, by leveraging the flexibility of IDS principle in choosing the learning target, we propose two methods for constructing compressed environments based on rate-distortion theory, upon which we develop an algorithm Compressed-MAIDS wherein the learning target is a compressed environment. Finally, we extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample-efficient manner.

本文设计并分析了一套基于信息导向采样（IDS）原理的多智能体强化学习（MARL）算法。这些算法从信息论的基本概念中获得灵感，并在MARL设置中被证明是样本效率高的，例如双人零和马尔可夫博弈（MGs）和多人一般和MGs。对于情景二人零和博弈，我们提出了三种样本效率算法来学习纳什均衡。其基本算法称为MAIDS，采用非对称学习结构，最大参与者首先根据联合策略的联合信息比解决最小最大优化问题，最小参与者在最大参与者的策略固定的情况下最小化边际信息比。理论分析表明，对于K集，它达到了O ~ (K)的贝叶斯遗憾。为了减少maid的计算量，我们开发了一种改进的Reg-MAIDS算法，该算法具有相同的贝叶斯遗憾界，同时具有更低的计算复杂度。此外，利用IDS原理在选择学习目标方面的灵活性，我们提出了两种基于率失真理论构建压缩环境的方法，并在此基础上开发了一种以压缩环境为学习目标的compressed - maids算法。最后，我们将regg - maids扩展到多玩家一般和博弈中，并证明了它可以以样本效率的方式学习纳什均衡或粗相关均衡。

{"title":"Provably efficient information-directed sampling algorithms for multi-agent reinforcement learning","authors":"Qiaosheng Zhang , Chenjia Bai , Shuyue Hu , Zhen Wang , Xuelong Li","doi":"10.1016/j.artint.2025.104392","DOIUrl":"10.1016/j.artint.2025.104392","url":null,"abstract":"<div><div>This work designs and analyzes a novel set of algorithms for multi-agent reinforcement learning (MARL) based on the principle of information-directed sampling (IDS). These algorithms draw inspiration from foundational concepts in information theory, and are proven to be sample efficient in MARL settings such as two-player zero-sum Markov games (MGs) and multi-player general-sum MGs. For episodic two-player zero-sum MGs, we present three sample-efficient algorithms for learning Nash equilibrium. The basic algorithm, referred to as <span>MAIDS</span>, employs an asymmetric learning structure where the max-player first solves a minimax optimization problem based on the <em>joint information ratio</em> of the joint policy, and the min-player then minimizes the <em>marginal information ratio</em> with the max-player's policy fixed. Theoretical analyses show that it achieves a Bayesian regret of <span><math><mover><mrow><mi>O</mi></mrow><mrow><mo>˜</mo></mrow></mover><mo>(</mo><msqrt><mrow><mi>K</mi></mrow></msqrt><mo>)</mo></math></span> for <em>K</em> episodes. To reduce the computational load of <span>MAIDS</span>, we develop an improved algorithm called <span>Reg-MAIDS</span>, which has the same Bayesian regret bound while enjoying less computational complexity. Moreover, by leveraging the flexibility of IDS principle in choosing the learning target, we propose two methods for constructing compressed environments based on rate-distortion theory, upon which we develop an algorithm <span>Compressed-MAIDS</span> wherein the learning target is a compressed environment. Finally, we extend <span>Reg-MAIDS</span> to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample-efficient manner.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104392"},"PeriodicalIF":5.1,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144613978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Relaxed core stability in hedonic games 在享乐游戏中放松核心稳定性

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-09 DOI: 10.1016/j.artint.2025.104394

Angelo Fanelli , Gianpiero Monaco , Luca Moscardelli

The core is a well-known and fundamental notion of stability in games intended to model coalition formation such as hedonic games: an outcome is core stable if there exists no blocking coalition, i.e., no set of agents that may profit by forming a coalition together. The fact that the cardinality of a blocking coalition, i.e., the number of deviating agents that have to coordinate themselves, can be arbitrarily high, and the fact that agents may benefit only by a tiny amount from their deviation, while they could incur in a higher cost for deviating, suggest that the core is not able to suitably model practical scenarios in large and highly distributed multi-agent systems. For this reason, we consider relaxed core stable outcomes where the notion of permissible deviations is modified along two orthogonal directions: the former takes into account the size q of the deviating coalition, and the latter the amount of utility gain, in terms of a multiplicative factor k, for each member of the deviating coalition. These changes result in two different notions of stability, namely, the q-size core and k-improvement core. We consider fractional hedonic games, that is a well-known subclass of hedonic games for which core stable outcomes are not guaranteed to exist and it is computationally hard to decide non-emptiness of the core; we investigate these relaxed concepts of stability with respect to their existence, computability and performance in terms of price of anarchy and price of stability, by providing in many cases tight or almost tight bounds. Interestingly, the considered relaxed notions of core also possess the appealing property of recovering, in some notable cases, the convergence, the existence and the possibility of computing stable solutions in polynomial time.

核心是游戏中一个众所周知的基本稳定性概念，用于模拟联盟的形成，如享乐游戏：如果不存在阻塞联盟，即没有一组代理可以通过组成联盟来获利，则结果是核心稳定的。事实上，阻塞联盟的基数，即必须协调自己的偏离代理的数量，可以任意高，并且代理可能只从他们的偏离中获得很小的收益，而他们可能会因偏离而产生更高的成本，这表明核心无法适当地模拟大型和高度分布式的多代理系统中的实际场景。出于这个原因，我们考虑宽松的核心稳定结果，其中允许偏差的概念沿着两个正交方向进行修改：前者考虑了偏离联盟的大小q，后者考虑了偏离联盟中每个成员的乘法因子k的效用增益量。这些变化导致了两种不同的稳定性概念，即q-size核心和k-improvement核心。我们考虑分数型享乐对策，这是一个众所周知的享乐对策的子类，它的核心稳定结果不能保证存在，并且计算上难以确定核心的非空性；我们通过在许多情况下提供紧或几乎紧的边界，从无政府状态的价格和稳定的价格的角度，研究了这些宽松的稳定性概念的存在性、可计算性和性能。有趣的是，所考虑的核的松弛概念也具有吸引人的性质，在一些值得注意的情况下，恢复了收敛性、存在性和在多项式时间内计算稳定解的可能性。

{"title":"Relaxed core stability in hedonic games","authors":"Angelo Fanelli , Gianpiero Monaco , Luca Moscardelli","doi":"10.1016/j.artint.2025.104394","DOIUrl":"10.1016/j.artint.2025.104394","url":null,"abstract":"<div><div>The <em>core</em> is a well-known and fundamental notion of stability in games intended to model coalition formation such as hedonic games: an outcome is core stable if there exists no <em>blocking coalition</em>, i.e., no set of agents that may profit by forming a coalition together. The fact that the cardinality of a blocking coalition, i.e., the number of deviating agents that have to coordinate themselves, can be arbitrarily high, and the fact that agents may benefit only by a tiny amount from their deviation, while they could incur in a higher cost for deviating, suggest that the core is not able to suitably model practical scenarios in large and highly distributed multi-agent systems. For this reason, we consider relaxed core stable outcomes where the notion of permissible deviations is modified along two orthogonal directions: the former takes into account the size <em>q</em> of the deviating coalition, and the latter the amount of utility gain, in terms of a multiplicative factor <em>k</em>, for each member of the deviating coalition. These changes result in two different notions of stability, namely, the <em>q-size core</em> and <em>k-improvement core</em>. We consider fractional hedonic games, that is a well-known subclass of hedonic games for which core stable outcomes are not guaranteed to exist and it is computationally hard to decide non-emptiness of the core; we investigate these relaxed concepts of stability with respect to their existence, computability and performance in terms of price of anarchy and price of stability, by providing in many cases tight or almost tight bounds. Interestingly, the considered relaxed notions of core also possess the appealing property of recovering, in some notable cases, the convergence, the existence and the possibility of computing stable solutions in polynomial time.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104394"},"PeriodicalIF":5.1,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144588462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the design of truthful mechanisms for the capacitated facility location problem with two and more facilities 两个及两个以上可容设施选址问题的真实机制设计

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-07 DOI: 10.1016/j.artint.2025.104390

Gennaro Auricchio , Zihe Wang , Jie Zhang

In this paper, we explore the Mechanism Design aspects of the m-Capacitated Facility Location Problem (m-CFLP) on a line, focusing on two frameworks. In the first framework, the number of facilities is arbitrary, all facilities share the same capacity, and the number of agents matches the total capacity of the facilities. In the second framework, we need to locate two facilities, each with a capacity equal to at least half the number of agents. For both frameworks, we propose truthful mechanisms with bounded approximation ratios in terms of Social Cost (SC) and Maximum Cost (MC). When

m > 2

, our results stand in contrast to the impossibility results known for the classical m-Facility Location Problem, where capacity constraints are absent. Moreover, all the proposed mechanisms are optimal with respect to MC and either optimal or near-optimal with respect to the SC among anonymous mechanisms. We then establish lower bounds on the approximation ratios that any truthful and deterministic mechanism achieves with respect to SC and MC for both frameworks. Lastly, we run several numerical experiments to empirically evaluate the performances of our mechanisms with respect to the SC or the MC. Our empirical analysis shows that our proposed mechanisms outperform all previously proposed mechanisms applicable in this setting.

在本文中，我们探讨了m-Capacitated设施选址问题（m-CFLP）在一条线上的机制设计方面，重点是两个框架。在第一个框架中，设施的数量是任意的，所有设施共享相同的容量，代理的数量与设施的总容量相匹配。在第二个框架中，我们需要找到两个设施，每个设施的容量至少等于代理数量的一半。对于这两个框架，我们提出了基于社会成本（SC）和最大成本（MC）的有界近似比的真实机制。当m>；2时，我们的结果与不存在容量约束的经典m-设施选址问题的不可能结果形成对比。此外，所有提出的机制都是最优的MC和最优或接近最优的SC在匿名机制。然后，我们建立了关于两个框架的SC和MC的任何真实和确定性机制所达到的近似比率的下界。最后，我们进行了几个数值实验，以经验性地评估我们的机制相对于SC或MC的性能。我们的实证分析表明，我们提出的机制优于所有先前提出的适用于此设置的机制。

{"title":"On the design of truthful mechanisms for the capacitated facility location problem with two and more facilities","authors":"Gennaro Auricchio , Zihe Wang , Jie Zhang","doi":"10.1016/j.artint.2025.104390","DOIUrl":"10.1016/j.artint.2025.104390","url":null,"abstract":"<div><div>In this paper, we explore the Mechanism Design aspects of the <em>m</em>-Capacitated Facility Location Problem (<em>m</em>-CFLP) on a line, focusing on two frameworks. In the first framework, the number of facilities is arbitrary, all facilities share the same capacity, and the number of agents matches the total capacity of the facilities. In the second framework, we need to locate two facilities, each with a capacity equal to at least half the number of agents. For both frameworks, we propose truthful mechanisms with bounded approximation ratios in terms of Social Cost (SC) and Maximum Cost (MC). When <span><math><mi>m</mi><mo>></mo><mn>2</mn></math></span>, our results stand in contrast to the impossibility results known for the classical <em>m</em>-Facility Location Problem, where capacity constraints are absent. Moreover, all the proposed mechanisms are optimal with respect to MC and either optimal or near-optimal with respect to the SC among anonymous mechanisms. We then establish lower bounds on the approximation ratios that any truthful and deterministic mechanism achieves with respect to SC and MC for both frameworks. Lastly, we run several numerical experiments to empirically evaluate the performances of our mechanisms with respect to the SC or the MC. Our empirical analysis shows that our proposed mechanisms outperform all previously proposed mechanisms applicable in this setting.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104390"},"PeriodicalIF":5.1,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Introduction to open-world AI 开放世界AI简介

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-04 DOI: 10.1016/j.artint.2025.104393

Lawrence Holder , Pat Langley , Bryan Loyall , Ted Senator

Open-world AI is characterized by sudden novel changes in a domain that are outside the scope of the training data, or the deployment of an agent in conditions that violate the implicit or explicit assumptions of the designer. In such situations, the AI system must detect the novelty and adapt in a short time frame. In this introduction to the special issue on open-world AI, we discuss the background and motivation for this new research area and define the field in the context of similar AI challenges. We then discuss recent research in the area that has made significant contributions to the field. Many of those contributions are reflected in the papers of this special issue, which we summarize alongside more traditional approaches to open-world AI. Finally, we discuss future directions for the field.

开放世界AI的特点是在训练数据范围之外的领域中突然出现新颖的变化，或者在违反设计师隐含或明确假设的条件下部署代理。在这种情况下，人工智能系统必须检测到新颖性并在短时间内适应。在这篇关于开放世界人工智能特刊的介绍中，我们讨论了这个新研究领域的背景和动机，并在类似人工智能挑战的背景下定义了这个领域。然后，我们讨论了该领域最近的研究，这些研究对该领域做出了重大贡献。其中许多贡献都反映在本期特刊的论文中，我们将其与更传统的开放世界AI方法一起进行总结。最后，我们讨论了该领域的未来发展方向。

引用次数: 0

Regression-based conditional independence test with adaptive kernels 基于回归的自适应核条件独立性检验

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-07-01 DOI: 10.1016/j.artint.2025.104391

Yixin Ren , Juncai Zhang , Yewei Xia , Ruxin Wang , Feng Xie , Jihong Guan , Hao Zhang , Shuigeng Zhou

We propose a novel framework for regression-based conditional independence (CI) test with adaptive kernels, where the task of CI test is reduced to regression and statistical independence test while proving that the test power of CI can be maximized by adaptively learning parameterized kernels of the independence test if the consistency of regression can be guaranteed. For the adaptively learning kernel of independence test, we first address the pitfall inherent in the existing signal-to-noise ratio criterion by modeling the change of the null distribution during the learning process, then design a new class of kernels that can adaptively focus on the significant dimensions of variables to judge independence, which makes the tests more flexible than using simple kernels that are adaptive only in length-scale, and especially suitable for high-dimensional complex data. Theoretically, we demonstrate the consistency of the proposed tests, and show that the non-convex objective function used for learning fits the L-smoothing condition, thus benefiting the optimization. Experimental results on both synthetic and real data show the superiority of our method. The source code and datasets are available at https://github.com/hzsiat/AdaRCIT.

提出了一种新的自适应核回归条件独立（CI）检验框架，将CI检验的任务简化为回归和统计独立性检验，同时证明了在保证回归一致性的前提下，通过自适应学习独立检验的参数化核，可以最大限度地提高CI的检验能力。对于独立性检验的自适应学习核，我们首先通过建模零分布在学习过程中的变化，解决了现有信噪比准则固有的缺陷，然后设计了一类新的核，可以自适应地关注变量的重要维度来判断独立性，这使得测试比使用仅在长度尺度上自适应的简单核更灵活。特别适用于高维复杂数据。理论上，我们证明了所提出的测试的一致性，并表明用于学习的非凸目标函数符合l -平滑条件，从而有利于优化。合成数据和实际数据的实验结果表明了该方法的优越性。源代码和数据集可从https://github.com/hzsiat/AdaRCIT获得。

{"title":"Regression-based conditional independence test with adaptive kernels","authors":"Yixin Ren , Juncai Zhang , Yewei Xia , Ruxin Wang , Feng Xie , Jihong Guan , Hao Zhang , Shuigeng Zhou","doi":"10.1016/j.artint.2025.104391","DOIUrl":"10.1016/j.artint.2025.104391","url":null,"abstract":"<div><div>We propose a novel framework for regression-based conditional independence (CI) test with adaptive kernels, where the task of CI test is reduced to regression and statistical independence test while proving that the test power of CI can be maximized by adaptively learning parameterized kernels of the independence test if the consistency of regression can be guaranteed. For the adaptively learning kernel of independence test, we first address the pitfall inherent in the existing signal-to-noise ratio criterion by modeling the change of the null distribution during the learning process, then design a new class of kernels that can adaptively focus on the significant dimensions of variables to judge independence, which makes the tests more flexible than using simple kernels that are adaptive only in length-scale, and especially suitable for high-dimensional complex data. Theoretically, we demonstrate the consistency of the proposed tests, and show that the non-convex objective function used for learning fits the L-smoothing condition, thus benefiting the optimization. Experimental results on both synthetic and real data show the superiority of our method. The source code and datasets are available at <span><span>https://github.com/hzsiat/AdaRCIT</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"347 ","pages":"Article 104391"},"PeriodicalIF":5.1,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fair distribution of delivery orders 公平分配交货订单

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-06-27 DOI: 10.1016/j.artint.2025.104389

Hadi Hosseini , Shivika Narang , Tomasz Wąs

We initiate the study of fair distribution of delivery tasks among a set of agents wherein delivery jobs are placed along the vertices of a graph. Our goal is to fairly distribute delivery costs (distance traveled to complete the deliveries) among a fixed set of agents while satisfying some desirable notions of economic efficiency. We adopt well-established fairness concepts—such as envy-freeness up to one item (EF1) and minimax share (MMS)—to our setting and show that fairness is often incompatible with the efficiency notion of social optimality. We then characterize instances that admit fair and socially optimal solutions by exploiting graph structures. We further show that achieving fairness along with Pareto optimality is computationally intractable. We complement this by designing an XP algorithm (parameterized by the number of agents) for finding MMS and Pareto optimal solutions on every tree instance, and show that the same algorithm can be modified to find efficient solutions along with EF1, when such solutions exist. The latter crucially relies on an intriguing result that in our setting EF1 and Pareto optimality jointly imply MMS. We conclude by theoretically and experimentally analyzing the price of fairness.

我们开始研究配送任务在一组代理之间的公平分配，其中配送任务沿着图的顶点放置。我们的目标是在一组固定的代理中公平分配配送成本（完成配送的距离），同时满足一些理想的经济效率概念。我们采用了公认的公平概念——例如最多一项嫉妒（EF1）和最小最大份额（MMS）——来进行我们的设置，并表明公平通常与社会最优的效率概念不相容。然后，我们通过利用图结构来描述承认公平和社会最优解的实例。我们进一步表明，实现公平与帕累托最优是计算难以处理的。我们通过设计一个XP算法（由代理数量参数化）来补充这一点，用于在每个树实例上寻找MMS和Pareto最优解，并表明当这样的解存在时，相同的算法可以被修改以找到与EF1一起的有效解。后者主要依赖于一个有趣的结果，即在我们的设置中，EF1和帕累托最优联合暗示MMS。本文通过对公平价格的理论分析和实验分析得出结论。

{"title":"Fair distribution of delivery orders","authors":"Hadi Hosseini , Shivika Narang , Tomasz Wąs","doi":"10.1016/j.artint.2025.104389","DOIUrl":"10.1016/j.artint.2025.104389","url":null,"abstract":"<div><div>We initiate the study of fair distribution of delivery tasks among a set of agents wherein delivery jobs are placed along the vertices of a graph. Our goal is to fairly distribute delivery costs (distance traveled to complete the deliveries) among a fixed set of agents while satisfying some desirable notions of economic efficiency. We adopt well-established fairness concepts—such as <em>envy-freeness up to one item</em> (EF1) and <em>minimax share</em> (MMS)—to our setting and show that fairness is often incompatible with the efficiency notion of <em>social optimality</em>. We then characterize instances that admit fair and socially optimal solutions by exploiting graph structures. We further show that achieving fairness along with Pareto optimality is computationally intractable. We complement this by designing an XP algorithm (parameterized by the number of agents) for finding MMS and Pareto optimal solutions on every tree instance, and show that the same algorithm can be modified to find efficient solutions along with EF1, when such solutions exist. The latter crucially relies on an intriguing result that in our setting EF1 and Pareto optimality jointly imply MMS. We conclude by theoretically and experimentally analyzing the price of fairness.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"347 ","pages":"Article 104389"},"PeriodicalIF":5.1,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144516138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A scalable multi-robot goal assignment algorithm for minimizing mission time followed by total movement cost 最小化任务时间和总运动成本的可扩展多机器人目标分配算法

IF 5.1 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-06-20 DOI: 10.1016/j.artint.2025.104388

Aakash, Indranil Saha

We study a variant of the multi-robot goal assignment problem where a unique goal for each robot needs to be assigned while minimizing the largest cost of movement among the robots, called makespan, and then minimizing the total movement cost of all the robots without exceeding the optimal makespan. A significant step in solving this problem is to find the cost associated with each robot-goal pair, which requires solving several complex path planning problems, thus, limiting the scalability. We present an algorithm that solves the multi-robot goal assignment problem by computing the paths for a significantly smaller number of robot-goal pairs compared to state-of-the-art algorithms, leading to a computationally superior mechanism to solve the problem. We perform theoretical analysis to establish the correctness and optimality of the proposed algorithm, as well as its worst-case polynomial time complexity. We extensively evaluate our algorithm for hundreds of robots on randomly generated and standard workspaces. Our experimental results demonstrate that the proposed algorithm achieves a noticeable speedup over two state-of-the-art baseline algorithms.

本文研究了多机器人目标分配问题的一种变体，即需要为每个机器人分配一个唯一的目标，同时使机器人之间的最大运动成本最小化（称为makespan），然后在不超过最优makespan的情况下使所有机器人的总运动成本最小化。解决该问题的一个重要步骤是找到每个机器人-目标对的相关成本，这需要解决几个复杂的路径规划问题，因此限制了可扩展性。我们提出了一种算法，该算法通过计算机器人-目标对的路径来解决多机器人目标分配问题，与最先进的算法相比，它的数量要少得多，从而产生了一种计算上优越的机制来解决问题。我们进行了理论分析，以确定所提出的算法的正确性和最优性，以及它的最坏情况多项式时间复杂度。我们在随机生成和标准工作空间上对数百个机器人广泛评估我们的算法。实验结果表明，该算法比两种最先进的基线算法实现了显著的加速。

{"title":"A scalable multi-robot goal assignment algorithm for minimizing mission time followed by total movement cost","authors":"Aakash, Indranil Saha","doi":"10.1016/j.artint.2025.104388","DOIUrl":"10.1016/j.artint.2025.104388","url":null,"abstract":"<div><div>We study a variant of the multi-robot goal assignment problem where a unique goal for each robot needs to be assigned while minimizing the largest cost of movement among the robots, called makespan, and then minimizing the total movement cost of all the robots without exceeding the optimal makespan. A significant step in solving this problem is to find the cost associated with each robot-goal pair, which requires solving several complex path planning problems, thus, limiting the scalability. We present an algorithm that solves the multi-robot goal assignment problem by computing the paths for a significantly smaller number of robot-goal pairs compared to state-of-the-art algorithms, leading to a computationally superior mechanism to solve the problem. We perform theoretical analysis to establish the correctness and optimality of the proposed algorithm, as well as its worst-case polynomial time complexity. We extensively evaluate our algorithm for hundreds of robots on randomly generated and standard workspaces. Our experimental results demonstrate that the proposed algorithm achieves a noticeable speedup over two state-of-the-art baseline algorithms.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"347 ","pages":"Article 104388"},"PeriodicalIF":5.1,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144337686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0