-
Non-deterministic approximation fixpoint theory and its application in disjunctive logic programming Artif. Intell. (IF 14.4) Pub Date : 2024-03-08 Jesse Heyninck, Ofer Arieli, Bart Bogaerts
Approximation fixpoint theory (AFT) is an abstract and general algebraic framework for studying the semantics of nonmonotonic logics. It provides a unifying study of the semantics of different formalisms for nonmonotonic reasoning, such as logic programming, default logic and autoepistemic logic. In this paper, we extend AFT to dealing with that allow to handle indefinite information, represented e
-
“Guess what I'm doing”: Extending legibility to sequential decision tasks Artif. Intell. (IF 14.4) Pub Date : 2024-03-07 Miguel Faria, Francisco S. Melo, Ana Paiva
In this paper we investigate the notion of in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive. Our proposed approach, dubbed PoLMDP, is able to handle uncertainty while remaining computationally tractable. We establish the advantages of our approach against
-
aspmc: New frontiers of algebraic answer set counting Artif. Intell. (IF 14.4) Pub Date : 2024-03-06 Thomas Eiter, Markus Hecher, Rafael Kiesel
In the last decade, there has been increasing interest in extensions of answer set programming (ASP) that cater for quantitative information such as weights or probabilities. A wide range of quantitative reasoning tasks for ASP and logic programming, among them probabilistic inference and parameter learning in the neuro-symbolic setting, can be expressed as algebraic answer set counting (AASC) tasks
-
Investigating the properties of neural network representations in reinforcement learning Artif. Intell. (IF 14.4) Pub Date : 2024-03-01 Han Wang, Erfan Miahi, Martha White, Marlos C. Machado, Zaheer Abbas, Raksha Kumaraswamy, Vincent Liu, Adam White
In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve properties thought to be desirable, such as orthogonality and sparsity. In contrast, the idea behind deep reinforcement learning methods is that the agent designer
-
Crossover can guarantee exponential speed-ups in evolutionary multi-objective optimisation Artif. Intell. (IF 14.4) Pub Date : 2024-02-27 Duc-Cuong Dang, Andre Opris, Dirk Sudholt
Evolutionary algorithms are popular algorithms for multi-objective optimisation (also called Pareto optimisation) as they use a population to store trade-offs between different objectives. Despite their popularity, the theoretical foundation of multi-objective evolutionary optimisation (EMO) is still in its early development. Fundamental questions such as the benefits of the crossover operator are
-
Datalog rewritability and data complexity of ALCHOIQ with closed predicates Artif. Intell. (IF 14.4) Pub Date : 2024-02-23 Sanja Lukumbuzya, Magdalena Ortiz, Mantas Šimkus
We study the relative expressiveness of ontology-mediated queries (OMQs) formulated in the expressive Description Logic extended with closed predicates. In particular, we present a polynomial time translation from OMQs into Datalog with negation under the stable model semantics, the formalism that underlies Answer Set Programming. This is a novel and non-trivial result: the considered OMQs are not
-
Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization Artif. Intell. (IF 14.4) Pub Date : 2024-02-21 Stewart Jamieson, Jonathan P. How, Yogesh Girdhar
We propose (EBRM) over policy sets as an approach to online learning across a wide range of settings. Many real-world online learning problems have complexities such as action- and belief-dependent rewards, time-discounting of reward, and heterogeneous costs for actions and feedback; we find that existing online learning heuristics cannot leverage most problem-specific information, to the detriment
-
Generalized planning as heuristic search: A new planning search-space that leverages pointers over objects Artif. Intell. (IF 14.4) Pub Date : 2024-02-15 Javier Segovia-Aguas, Sergio Jiménez, Anders Jonsson
is one of the most successful approaches to but unfortunately, it does not trivially extend to (GP); GP aims to compute algorithmic solutions that are valid for a set of classical planning instances from a given domain, even if these instances differ in their number of objects, the initial and goal configuration of these objects and hence, in the number (and possible values) of the state variables
-
Decentralized Fused-Learner Architectures for Bayesian Reinforcement Learning Artif. Intell. (IF 14.4) Pub Date : 2024-02-13 Augustin A. Saucan, Subhro Das, Moe Z. Win
Decentralized training is a robust solution for learning over an extensive network of distributed agents. Many existing solutions involve the averaging of locally inferred parameters which constrain the architecture to independent agents with identical learning algorithms. Here, we propose decentralized fused-learner architectures for Bayesian reinforcement learning, named fused Bayesian-learner architectures
-
Temporal Segmentation in Multi Agent Path Finding with Applications to Explainability Artif. Intell. (IF 14.4) Pub Date : 2024-02-07 Shaull Almagor, Justin Kottinger, Morteza Lahijanian
Multi-Agent Path Finding (MAPF) is the problem of planning paths for agents to reach their targets from their start locations, such that the agents do not collide while executing the plan. In many settings, the plan (or a digest thereof) is conveyed to a supervising entity, e.g., for confirmation before execution, for a report, etc. In such cases, we wish to convey that the plan is collision-free with
-
Primarily about primaries Artif. Intell. (IF 14.4) Pub Date : 2024-02-07 Allan Borodin, Omer Lev, Nisarg Shah, Tyrone Strangway
Much of the social choice literature examines voting systems, in which voters submit their ranked preferences over candidates and a voting rule picks a winner. Real-world elections and decision-making processes are often more complex and involve multiple stages. For instance, one popular voting system filters candidates through : first, voters affiliated with each political party vote over candidates
-
An extended view on lifting Gaussian Bayesian networks Artif. Intell. (IF 14.4) Pub Date : 2024-02-06 Mattis Hartwig, Ralf Möller, Tanya Braun
Lifting probabilistic graphical models and developing lifted inference algorithms aim to use higher level groups of random variables instead of individual instances. In the past, many inference algorithms for discrete probabilistic graphical models have been lifted. Lifting continuous probabilistic graphical models has played a minor role. Since many real-world applications involve continuous random
-
-
Pre-training and diagnosing knowledge base completion models Artif. Intell. (IF 14.4) Pub Date : 2024-02-02 Vid Kocijan, Myeongjun Jang, Thomas Lukasiewicz
In this work, we introduce and analyze an approach to knowledge transfer from one collection of facts to another without the need for entity or relation matching. The method works for both knowledge bases and or , i.e., knowledge bases where more than one copy of a real-world entity or relation may exist. The main contribution is a method that can make use of large-scale pre-training on facts, which
-
Revision operators with compact representations Artif. Intell. (IF 14.4) Pub Date : 2024-02-02 Pavlos Peppas, Mary-Anne Williams, Grigoris Antoniou
Despite the great theoretical advancements in the area of Belief Revision, there has been limited success in terms of implementations. One of the hurdles in implementing revision operators is that their specification (let alone their computation), requires substantial resources. On the other hand, implementing a specific revision operator, like Dalal's operator, would be of limited use. In this paper
-
Efficient optimal Kolmogorov approximation of random variables Artif. Intell. (IF 14.4) Pub Date : 2024-02-01 Liat Cohen, Tal Grinshpoun, Gera Weiss
Discrete random variables are essential ingredients in various artificial intelligence problems. These include the estimation of the probability of missing the deadline in a series-parallel schedule and the assignment of suppliers to tasks in a project in a manner that maximizes the probability of meeting the overall project deadline. The solving of such problems involves repetitive operations, such
-
A stochastic process approach for multi-agent path finding with non-asymptotic performance guarantees Artif. Intell. (IF 14.4) Pub Date : 2024-02-01 Xiaoyu He, Xueyan Tang, Wentong Cai, Jingning Li
Multi-agent path finding (MAPF) is a classical NP-hard problem that considers planning collision-free paths for multiple agents simultaneously. A MAPF problem is typically solved via addressing a sequence of single-agent path finding subproblems in which well-studied algorithms such as are applicable. Existing methods based on this idea, however, rely on an exhaustive search and therefore only have
-
Temporal inductive path neural network for temporal knowledge graph reasoning Artif. Intell. (IF 14.4) Pub Date : 2024-02-01 Hao Dong, Pengyang Wang, Meng Xiao, Zhiyuan Ning, Pengfei Wang, Yuanchun Zhou
Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge Graph (KG) that incorporates the dimension of time. Reasoning on TKGs is a crucial task that aims to predict future facts based on historical occurrences. The key challenge lies in uncovering structural dependencies within historical subgraphs and temporal patterns. Most existing approaches model TKGs relying on entity modeling
-
Transferable dynamics models for efficient object-oriented reinforcement learning Artif. Intell. (IF 14.4) Pub Date : 2024-01-26 Ofir Marom, Benjamin Rosman
The Reinforcement Learning (RL) framework offers a general paradigm for constructing autonomous agents that can make effective decisions when solving tasks. An important area of study within the field of RL is transfer learning, where an agent utilizes knowledge gained from solving previous tasks to solve a new task more efficiently. While the notion of transfer learning is conceptually appealing,
-
Emotion Selectable End-to-End Text-based Speech Editing Artif. Intell. (IF 14.4) Pub Date : 2024-01-23 Tao Wang, Jiangyan Yi, Ruibo Fu, Jianhua Tao, Zhengqi Wen, Chu Yuan Zhang
Text-based speech editing is a convenient way for users to edit speech by intuitively cutting, copying, and pasting text. Previous work introduced CampNet, a context-aware mask prediction network that significantly improved the quality of edited speech. However, this paper proposes a new task: adding emotional effects to the edited speech during text-based speech editing to enhance the expressiveness
-
Saliency-aware regularized graph neural network Artif. Intell. (IF 14.4) Pub Date : 2024-01-19 Wenjie Pei, WeiNa Xu, Zongze Wu, Weichao Li, Jinfan Wang, Guangming Lu, Xiangrong Wang
The crux of graph classification lies in the effective representation learning for the entire graph. Typical graph neural networks focus on modeling the local dependencies when aggregating features of neighboring nodes, and obtain the representation for the entire graph by aggregating node features. Such methods have two potential limitations: 1) the global node saliency w.r.t. graph classification
-
Counterexamples and amendments to the termination and optimality of ADOPT-based algorithms Artif. Intell. (IF 14.4) Pub Date : 2024-01-24 Koji Noshiro, Koji Hasebe
A distributed constraint optimization problem (DCOP) is a framework to model multi-agent coordination problems. Asynchronous distributed optimization (ADOPT) is a well-known complete DCOP algorithm, and many of its variants have been proposed over the last decade. It is considered proven that ADOPT-based algorithms have the key properties of termination and optimality, which guarantee that the algorithms
-
Enhancing SMT-based Weighted Model Integration by structure awareness Artif. Intell. (IF 14.4) Pub Date : 2024-01-18 Giuseppe Spallitta, Gabriele Masina, Paolo Morettin, Andrea Passerini, Roberto Sebastiani
The development of efficient exact and approximate algorithms for probabilistic inference is a long-standing goal of artificial intelligence research. Whereas substantial progress has been made in dealing with purely discrete or purely continuous domains, adapting the developed solutions to tackle hybrid domains, characterized by discrete and continuous variables and their relationships, is highly
-
On the role of logical separability in knowledge compilation Artif. Intell. (IF 14.4) Pub Date : 2024-01-12 Junming Qiu, Wenqing Li, Liangda Fang, Quanlong Guan, Zhanhao Xiao, Zhao-Rong Lai, Qian Dong
Knowledge compilation is an alternative solution to address demanding reasoning tasks with high complexity via converting knowledge bases into a suitable target language. The notion of logical separability, proposed by Levesque, offers a general explanation for the tractability of clausal entailment for two remarkable languages: decomposable negation normal form and prime implicates. It is interesting
-
Dual-track spatio-temporal learning for urban flow prediction with adaptive normalization Artif. Intell. (IF 14.4) Pub Date : 2024-01-15 Xiaoyu Li, Yongshun Gong, Wei Liu, Yilong Yin, Yu Zheng, Liqiang Nie
Robust urban flow prediction is crucial for transportation planning and management in urban areas. Although recent advances in modeling spatio-temporal correlations have shown potential, most models fail to adequately consider the complex spatio-temporal semantic information present in real-world scenarios. We summarize the following three primary limitations in existing models: a) The majority of
-
Corrigendum to “Learning constraints through partial queries” [Artificial Intelligence 319 (2023) 103896] Artif. Intell. (IF 14.4) Pub Date : 2024-01-12 Christian Bessiere, Clément Carbonnel, Anton Dries, Emmanuel Hebrard, George Katsirelos, Nadjib Lazaar, Nina Narodytska, Claude-Guy Quimper, Kostas Stergiou, Dimosthenis C. Tsouros, Toby Walsh
Abstract not available
-
The computational complexity of multi-agent pathfinding on directed graphs Artif. Intell. (IF 14.4) Pub Date : 2024-01-09 Bernhard Nebel
While the non-optimizing variant of multi-agent pathfinding on undirected graphs is known to be a polynomial-time problem since almost forty years, a similar result has not been established for directed graphs. In this paper, it will be shown that this problem is NP-complete. For strongly connected directed graphs, however, the problem is polynomial. And both of these results hold even if one allows
-
The Distortion of Distributed Facility Location Artif. Intell. (IF 14.4) Pub Date : 2024-01-09 Aris Filos-Ratsikas, Panagiotis Kanellopoulos, Alexandros A. Voudouris, Rongsen Zhang
We study the distributed facility location problem, where a set of agents with positions on the line of real numbers are partitioned into disjoint districts, and the goal is to choose a point to satisfy certain criteria, such as optimize an objective function or avoid strategic behavior. A mechanism in our distributed setting works in two steps: For each district it chooses a point that is representative
-
-
An attention model for the formation of collectives in real-world domains Artif. Intell. (IF 14.4) Pub Date : 2024-01-09 Adrià Fenoy, Filippo Bistaffa, Alessandro Farinelli
We consider the problem of forming collectives of agents inherent in application domains aligned with Sustainable Development Goals 4 and 11 (i.e., team formation and ridesharing, respectively). We propose a general solution approach based on a novel combination of an attention model and an integer linear program (ILP). In more detail, we propose an attention encoder-decoder model that transforms a
-
From statistical relational to neurosymbolic artificial intelligence: A survey Artif. Intell. (IF 14.4) Pub Date : 2024-01-09 Giuseppe Marra, Sebastijan Dumančić, Robin Manhaeve, Luc De Raedt
This survey explores the integration of learning and reasoning in two different fields of artificial intelligence: neurosymbolic and statistical relational artificial intelligence. Neurosymbolic artificial intelligence (NeSy) studies the integration of symbolic reasoning and neural networks, while statistical relational artificial intelligence (StarAI) focuses on integrating logic with probabilistic
-
Self-adjusting offspring population sizes outperform fixed parameters on the cliff function Artif. Intell. (IF 14.4) Pub Date : 2023-12-21 Mario Alejandro Hevia Fajardo, Dirk Sudholt
In the discrete domain, self-adjusting parameters of evolutionary algorithms (EAs) have emerged as a fruitful research area with many runtime analyses showing that self-adjusting parameters can outperform the best fixed parameters. Most existing runtime analyses focus on elitist EAs on simple problems, for which moderate performance gains were shown. Here we consider a much more challenging scenario:
-
Exploratory machine learning with unknown unknowns Artif. Intell. (IF 14.4) Pub Date : 2023-12-19 Peng Zhao, Jia-Wei Shan, Yu-Jie Zhang, Zhi-Hua Zhou
In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there are unknown classes in the training data misperceived as other labels, and thus their existence appears unknown from the given supervision. We attribute the unknown
-
Fragility, robustness and antifragility in deep learning Artif. Intell. (IF 14.4) Pub Date : 2023-12-19 Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha
We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifies the fragility, robustness and antifragility characteristics of DNN parameters. Our proposed analysis investigates if the DNN performance is impacted negatively, invariantly, or positively on both clean and adversarially
-
Evolving interpretable decision trees for reinforcement learning Artif. Intell. (IF 14.4) Pub Date : 2023-12-16 Vinícius G. Costa, Jorge Pérez-Aracil, Sancho Salcedo-Sanz, Carlos E. Pedreira
In recent years, reinforcement learning (RL) techniques have achieved great success in many different applications. However, their heavy reliance on complex deep neural networks makes most RL models uninterpretable, limiting their application in domains where trust and security are important. To address this challenge, we propose MENS-DT-RL, an algorithm capable of constructing interpretable models
-
Is this a violation? Learning and understanding norm violations in online communities Artif. Intell. (IF 14.4) Pub Date : 2023-12-15 Thiago Freitas dos Santos, Nardine Osman, Marco Schorlemmer
Using norms to guide and coordinate interactions has gained tremendous attention in the multi-agent community. However, new challenges arise as the interest moves towards dynamic socio-technical systems, where human and software agents interact, and interactions are required to adapt to human's changing needs. For instance, different agents (human or software) might not have the same understanding
-
-
Improved maximin guarantees for subadditive and fractionally subadditive fair allocation problem Artif. Intell. (IF 14.4) Pub Date : 2023-12-07 Masoud Seddighin, Saeed Seddighin
In this work, we study the maximin share fairness notion (MMS) for allocation of indivisible goods in the subadditive and fractionally subadditive settings. While previous work refutes the possibility of obtaining an allocation which is better than 1/2-MMS, the only positive result for the subadditive setting states that when the number of items is equal to m, there always exists an Ω(1/logm)-MMS
-
Negotiation strategies for agents with ordinal preferences: Theoretical analysis and human study Artif. Intell. (IF 14.4) Pub Date : 2023-12-04 Noam Hazon, Sefi Erlich, Ariel Rosenfeld, Sarit Kraus
Negotiation is a very common interaction between agents. Many common negotiation protocols work with cardinal utilities, even though ordinal preferences, which only rank the outcomes, are easier to elicit from humans. In this work, we focus on negotiation with ordinal preferences over a finite set of outcomes. We study an intuitive protocol for bilateral negotiations, where the two parties make offers
-
Pessimistic value iteration for multi-task data sharing in Offline Reinforcement Learning Artif. Intell. (IF 14.4) Pub Date : 2023-11-20 Chenjia Bai, Lingxiao Wang, Jianye Hao, Zhuoran Yang, Bin Zhao, Zhen Wang, Xuelong Li
Offline Reinforcement Learning (RL) has shown promising results in learning a task-specific policy from a fixed dataset. However, successful offline RL often relies heavily on the coverage and quality of the given dataset. In scenarios where the dataset for a specific task is limited, a natural approach is to improve offline RL with datasets from other tasks, namely, to conduct Multi-Task Data Sharing
-
Approximately EFX allocations for indivisible chores Artif. Intell. (IF 14.4) Pub Date : 2023-11-07 Shengwei Zhou, Xiaowei Wu
In this paper, we study how to fairly allocate a set of m indivisible chores to a group of n agents, each of which has a general additive cost function on the items. Since envy-free (EF) allocations are not guaranteed to exist, we consider the notion of envy-freeness up to any item (EFX). In contrast to the fruitful results regarding the (approximation of) EFX allocations for goods, very little is
-
Sound and relatively complete belief Hoare logic for statistical hypothesis testing programs Artif. Intell. (IF 14.4) Pub Date : 2023-11-10 Yusuke Kawamoto, Tetsuya Sato, Kohei Suenaga
We propose a new approach to formally describing the requirement for statistical inference and checking whether a program uses the statistical method appropriately. Specifically, we define belief Hoare logic (BHL) for formalizing and reasoning about the statistical beliefs acquired via hypothesis testing. This program logic is sound and relatively complete with respect to a Kripke model for hypothesis
-
Gerrymandering individual fairness Artif. Intell. (IF 14.4) Pub Date : 2023-10-24 Tim Räz
Individual fairness requires that similar individuals are treated similarly. It is supposed to prevent the unfair treatment of individuals on the subgroup level and to overcome the problem that group fairness measures are susceptible to manipulation or gerrymandering. The goal of the present paper is to explore the extent to which individual fairness itself can be gerrymandered. It will be proved that
-
Dual forgetting operators in the context of weakest sufficient and strongest necessary conditions Artif. Intell. (IF 14.4) Pub Date : 2023-10-23 Patrick Doherty, Andrzej Szałas
Forgetting is an important concept in knowledge representation and automated reasoning with widespread applications across a number of disciplines. A standard forgetting operator, characterized in [26] in terms of model-theoretic semantics and primarily focusing on the propositional case, opened up a new research subarea. In this paper, a new operator called weak forgetting, dual to standard forgetting
-
Distributed web hacking by adaptive consensus-based reinforcement learning Artif. Intell. (IF 14.4) Pub Date : 2023-10-24 Nemanja Ilić, Dejan Dašić, Miljan Vučetić, Aleksej Makarov, Ranko Petrović
In this paper, we propose a novel adaptive consensus-based learning algorithm for automated and distributed web hacking. We aim to assist ethical hackers in conducting legitimate penetration testing and improving web security by identifying system vulnerabilities at an early stage. Ethical hacking is modeled as a capture-the-flag style task addressed within a distributed reinforcement learning framework
-
Syntactic ASP forgetting with forks Artif. Intell. (IF 14.4) Pub Date : 2023-10-20 Felicidad Aguado, Pedro Cabalar, Jorge Fandinno, David Pearce, Gilberto Pérez, Concepción Vidal
Answer Set Programming (ASP) constitutes nowadays one of the most successful paradigms for practical Knowledge Representation and declarative problem solving. The formal analysis of ASP programs is essential for a rigorous treatment of specifications, the correct construction of solvers and the extension with other representational features. In this paper, we present a syntactic transformation, called
-
Extending the Description Logic EL with Threshold Concepts Induced by Concept Measures Artif. Intell. (IF 14.4) Pub Date : 2023-10-20 Franz Baader, Oliver Fernández Gil
In applications of AI systems where exact definitions of the important notions of the application domain are hard to come by, the use of traditional logic-based knowledge representation languages such as Description Logics may lead to very large and unintuitive definitions, and high complexity of reasoning. To overcome this problem, we define new concept constructors that allow us to define concepts
-
Ascending-price mechanism for general multi-sided markets Artif. Intell. (IF 14.4) Pub Date : 2023-10-10 Dvir Gilor, Rica Gonen, Erel Segal-Halevi
We present an ascending-price mechanism for a multi-sided market with a variety of participants, such as manufacturers, logistics agents, insurance providers, and assemblers. Each deal in the market may consist of a combination of agents from separate categories, and different such combinations are simultaneously allowed. This flexibility lets multiple intersecting markets be resolved as a single global
-
Risk-averse receding horizon motion planning for obstacle avoidance using coherent risk measures Artif. Intell. (IF 14.4) Pub Date : 2023-10-10 Anushri Dixit, Mohamadreza Ahmadi, Joel W. Burdick
This paper studies the problem of risk-averse receding horizon motion planning for agents with uncertain dynamics, in the presence of stochastic, dynamic obstacles. We propose a model predictive control (MPC) scheme that formulates the obstacle avoidance constraint using coherent risk measures. To handle disturbances, or process noise, in the state dynamics, the state constraints are tightened in a
-
Language, Common Sense, and the Winograd Schema Challenge Artif. Intell. (IF 14.4) Pub Date : 2023-10-06 Jacob Browning, Yann LeCun
Since the 1950s, philosophers and AI researchers have held that disambiguating natural language sentences depended on common sense. In 2011, the Winograd Schema Challenge was established to evaluate the common-sense reasoning abilities of a machine by testing its ability to disambiguate sentences. The designers argued only a system capable of “thinking in the full-bodied sense” would be able to pass
-
Robust Vehicle Lane Keeping Control with Networked Proactive Adaptation Artif. Intell. (IF 14.4) Pub Date : 2023-09-28 Hunmin Kim, Wenbin Wan, Naira Hovakimyan, Lui Sha, Petros Voulgaris
Road condition is an important environmental factor for autonomous vehicle control. A dramatic change in the road condition from the nominal status is a source of uncertainty that can lead to a system failure. Once the vehicle encounters an uncertain environment, such as hitting an ice patch, it is too late to reduce the speed, and the vehicle can lose control. To cope with unforeseen uncertainties
-
DEED: DEep Evidential Doctor Artif. Intell. (IF 14.4) Pub Date : 2023-09-28 Awais Ashfaq, Markus Lingman, Murat Sensoy, Sławomir Nowaczyk
As Deep Neural Networks (DNN) make their way into safety-critical decision processes, it becomes imperative to have robust and reliable uncertainty estimates for their predictions for both in-distribution and out-of-distribution (OOD) examples. This is particularly important in real-life high-risk settings such as healthcare, where OOD examples (e.g., patients with previously unseen or rare labels
-
Balanced Q-learning: Combining the influence of optimistic and pessimistic targets Artif. Intell. (IF 14.4) Pub Date : 2023-09-28 Thommen George Karimpanal, Hung Le, Majid Abdolshah, Santu Rana, Sunil Gupta, Truyen Tran, Svetha Venkatesh
The optimistic nature of the Q−learning target leads to an overestimation bias, which is an inherent problem associated with standard Q−learning. Such a bias fails to account for the possibility of low returns, particularly in risky scenarios. However, the existence of biases, whether overestimation or underestimation, need not necessarily be undesirable. In this paper, we analytically examine the
-
A general framework for preferences in answer set programming Artif. Intell. (IF 14.4) Pub Date : 2023-09-27 Gerhard Brewka, James Delgrande, Javier Romero, Torsten Schaub
We introduce a general, flexible, and extensible framework for quantitative and qualitative preferences among the stable models of logic programs. Since it is straightforward to capture propositional theories and constraint satisfaction problems with logic programs, our approach is also relevant to optimization in satisfiability testing and constraint processing. We show how complex preference relations
-
Hedonic diversity games: A complexity picture with more than two colors Artif. Intell. (IF 14.4) Pub Date : 2023-09-26 Robert Ganian, Thekla Hamm, Dušan Knop, Šimon Schierreich, Ondřej Suchý
Hedonic diversity games are a variant of the classical hedonic games designed to better model a variety of questions concerning diversity and fairness. Previous works mainly targeted the case with two diversity classes (represented as colors in the model) and provided some initial complexity-theoretic and existential results concerning Nash and individually stable outcomes. Here, we design new algorithms
-
Mathematical runtime analysis for the non-dominated sorting genetic algorithm II (NSGA-II) Artif. Intell. (IF 14.4) Pub Date : 2023-09-22 Weijie Zheng, Benjamin Doerr
The non-dominated sorting genetic algorithm II (NSGA-II) is the most intensively used multi-objective evolutionary algorithm (MOEA) in real-world applications. However, in contrast to several simple MOEAs analyzed also via mathematical means, no such study exists for the NSGA-II so far. In this work, we show that mathematical runtime analyses are feasible also for the NSGA-II. As particular results
-
A k-additive Choquet integral-based approach to approximate the SHAP values for local interpretability in machine learning Artif. Intell. (IF 14.4) Pub Date : 2023-09-19 Guilherme Dean Pelegrina, Leonardo Tomazeli Duarte, Michel Grabisch
Besides accuracy, recent studies on machine learning models have been addressing the question on how the obtained results can be interpreted. Indeed, while complex machine learning models are able to provide very good results in terms of accuracy even in challenging applications, it is difficult to interpret them. Aiming at providing some interpretability for such models, one of the most famous methods
-
Computing optimal hypertree decompositions with SAT Artif. Intell. (IF 14.4) Pub Date : 2023-09-18 André Schidler, Stefan Szeider
Hypertree width is a prominent hypergraph invariant with many algorithmic applications in constraint satisfaction and databases. We propose two novel characterisations for hypertree width in terms of linear orderings. We utilize these characterisations to obtain SAT, MaxSAT, and SMT encodings for computing the hypertree width exactly. We evaluate the encodings on an extensive set of benchmark instances
-
TEAMSTER: Model-based reinforcement learning for ad hoc teamwork Artif. Intell. (IF 14.4) Pub Date : 2023-09-15 João G. Ribeiro, Gonçalo Rodrigues, Alberto Sardinha, Francisco S. Melo
This paper investigates the use of model-based reinforcement learning in the context of ad hoc teamwork. We introduce a novel approach, named TEAMSTER, where we propose learning both the environment's model and the model of the teammates' behavior separately. Compared to the state-of-the-art PLASTIC algorithms, our results in four different domains from the multi-agent systems literature show that
-
Risk-aware autonomous localization in harsh urban environments with mosaic zonotope shadow matching Artif. Intell. (IF 14.4) Pub Date : 2023-09-11 Daniel Neamati, Sriramya Bhamidipati, Grace Gao
Urban localization with the Global Navigation Satellite System (GNSS) remains an unsolved problem with frequent misdetection of which street or which side of the street the user is located. 3D mapping-aided GNSS uses grid-based GNSS shadow matching and ranging alongside data-driven line-of-sight (LOS) classifiers to improve localization accuracy. However, previous work on shadow matching has not considered