Computational Agents Research Articles

Inference-Based Information Relevance Reasoning Method in Situation Assessment

The growing volume of information available to decision-makers makes it increasingly challenging to process all data during decision-making. As a result, a method for selecting only relevant information is highly desirable. Moreover, since the meaning of information depends on its context, the decision-making process requires mechanisms to identify the context of specific scenarios. In this paper, we propose a conceptual framework that utilizes Situation Theory to formalize the concept of context and analyze information relevance. Building on this framework, we introduce an inference-based reasoning process that automatically identifies the information necessary to characterize a given situation. We evaluate our approach in a cybersecurity scenario where computer agents respond to queries by utilizing available information and sharing relevant facts with other agents. The results show that our method significantly reduces the time required to infer answers to situation-specific queries. Additionally, we demonstrate that using only relevant information provides the same answers as using the entire knowledge base. Finally, we show that the method can be applied to a limited set of training queries, allowing the reuse of relevant facts to address new queries effectively.

A computational model reveals an early transient decrease in fiber cross-linking that unlocks adult regeneration

The decline in regeneration efficiency after birth in mammals is a significant roadblock for regenerative medicine in tissue repair. We previously developed a computational agent based-model (ABM) that recapitulates mechanical interactions between cells and the extracellular-matrix (ECM), to investigate key drivers of tissue repair in adults. Time calibration alongside a parameter sensitivity analysis of the model suggested that an early and transient decrease in ECM cross-linking guides tissue repair toward regeneration. Consistent with the computational model, transient inhibition or stimulation of fiber cross-linking for the first six days after subcutaneous adipose tissue (AT) resection in adult mice led to regenerative or scar healing, respectively. Therefore, this work positions the computational model as a predictive tool for tissue regeneration that with further development will behave as a digital twin of our in vivo model. In addition, it opens new therapeutic approaches targeting ECM cross-linking to induce tissue regeneration in adult mammals.

Decode, Move and Speak! Self-supervised Learning of Speech Units, Gestures, and Sound Relationships Using Vocal Imitation

Abstract Speech learning encompasses mastering a complex motor system to produce speech sounds from articulatory gestures while simultaneously uncovering discrete units that provide entry to the linguistic system. Remarkably, children acquire these associations between speech sounds, articulatory gestures, and linguistic units in a weakly supervised manner, without the need for explicit labeling of auditory inputs or access to target articulatory gestures. This study uses self-supervised deep learning to investigate the respective roles of sounds, gestures, and linguistic units in speech acquisition and control. In a first experiment, we analyzed the quantized representations learned by vector-quantized variational autoencoders (VQ-VAE) from ground truth acoustic and articulatory data using ABX tests. We show an interesting complementarity between acoustic and articulatory modalities that may help in the discovery of phonemes. In a second experiment, we introduce a computational agent that repeats auditory speech inputs by controlling a virtual vocal apparatus. This agent integrates an articulatory synthesizer capable of reproducing diverse speech stimuli from interpretable parameters, along with two internal models implementing the articulatory-to-acoustic (forward) and acoustic-to-articulatory (inverse) mapping, respectively. Additionally, two inductive biases are used to regularize the ill-posed acoustic-to-articulatory inverse mapping. In line with the first experiment, we explore the complementarity between the auditory input and the articulatory parameters inferred by the agent. We also evaluate the impact of discretizing auditory inputs using VQ-VAE. While the majority of the agent’s productions are intelligible (according to perceptual evaluations), our analysis highlights inconsistencies in the underlying articulatory trajectories. In particular, we show that the agent’s productions only partially reproduce the complementarity between the auditory and articulatory modalities observed in humans.

Urban Vulnerability Assessment of Sea Level Rise in Singapore through the World Avatar

This paper explores the application of The World Avatar (TWA) dynamic knowledge graph to connect isolated data and assess the impact of rising sea levels in Singapore. Current sea level rise vulnerability assessment tools are often regional, narrow in scope (e.g., economic or cultural aspects only), and are inadequate in representing complex non-geospatial data consistently. We apply TWA to conduct a multi-perspective impact assessment of sea level rise in Singapore, evaluating vulnerable buildings, road networks, land plots, cultural sites, and populations. We introduce OntoSeaLevel, an ontology to describe sea level rise scenarios, and its impact on broader elements defined in other ontologies such as buildings (OntoBuiltEnv ontology), road networks (OpenStreetMap ontology), and land plots (Ontoplot and Ontozoning ontology). We deploy computational agents to synthesise data from government, industry, and other publicly accessible sources, enriching buildings with metadata such as property usage, estimated construction cost, number of floors, and gross floor area. An agent is applied to identify and instantiate the impacted sites using OntoSeaLevel. These sites include vulnerable buildings, land plots, cultural sites, and populations at risk. We showcase these sea level rise vulnerable elements in a unified visualisation, demonstrating TWA’s potential as a planning tool against sea level rise through vulnerability assessment, resource allocation, and integrated spatial planning.

Learning Proficient Behavior With Computational Agents in Engineering Configuration Design

Abstract A novel approach for computational agents to learn proficient behavior in engineering configuration design that is inspired by human learning is introduced in this work. The learning proficient simulated annealing design agents (LPSADA) begin as different proficiency designers and are explicitly modeled to mimic the design behavior and performance of different proficiency human designers. A learning methodology, which is inspired by human learning, is introduced to update the characteristics of the agents that dictate their behavior. The methods are designed to change their behavioral characteristics based on their experience, including a non-deterministic reinforcement learning algorithm. Results show that the lower-proficiency agents successfully change their behavior to act more like high-proficiency designers. These behavior changes are shown to increase the performance of the lower-proficiency agents to the levels of high-proficiency human designers. In sum, the learning methodology that is introduced is shown to allow lower-proficiency agents to become higher-proficiency designers.

Foundations & Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions

Multimodal machine learning is a vibrant multi-disciplinary research field that aims to design computer agents with intelligent capabilities such as understanding, reasoning, and learning through integrating multiple communicative modalities, including linguistic, acoustic, visual, tactile, and physiological messages. With the recent interest in video understanding, embodied autonomous agents, text-to-image generation, and multisensor fusion in application domains such as healthcare and robotics, multimodal machine learning has brought unique computational and theoretical challenges to the machine learning community given the heterogeneity of data sources and the interconnections often found between modalities. However, the breadth of progress in multimodal research has made it difficult to identify the common themes and open questions in the field. By synthesizing a broad range of application domains and theoretical frameworks from both historical and recent perspectives, this article is designed to provide an overview of the computational and theoretical foundations of multimodal machine learning. We start by defining three key principles of modality heterogeneity , connections , and interactions that have driven subsequent innovations, and propose a taxonomy of six core technical challenges: representation , alignment , reasoning , generation , transference , and quantification covering historical and recent trends. Recent technical achievements will be presented through the lens of this taxonomy, allowing researchers to understand the similarities and differences across new approaches. We end by motivating several open problems for future research as identified by our taxonomy.

Intermedial and theatrical perspectives of AI: Re-framing the Turing test

Artificial intelligence (AI), the understanding and building of computational agents that act intelligently, is claimed to be a powerful, pervasive medium. Although we interact with it and hear a lot about it, we do not ‘see’ AI but experience its manifestations and/or outcomes, such as chatterbots and virtual assistants. A criterion for deeming an artificial agent as intelligent has been already proposed by Turing in 1950, coined as the ‘Imitation Game’, where a machine takes the place of a man, known as the Turing test. Despite the test being initially conceived as a make-believe game, AI has been enmeshed in major fields of human social activity and co-determines our lives. In this article, AI is compared with the media type of theatre performance, the epitome of make-believe, on the basis of intermediality. Furthermore, the analogies between AI and theatre are discussed and the paradigm of the puppet theatre as well as the medium of the mask prevail in the analysis. Findings are discussed, especially in light of the mind–body split and the alignment problem, and their implications are contemplated, allowing a re-estimation and re-framing of the Turing test in its theatrical and performative dimension.

Dynamic knowledge graph approach for modelling the decarbonisation of power systems

This paper presents a dynamic knowledge graph approach that offers a reusable, interoperable, and extensible framework for modelling power systems. Domain ontologies have been developed to support a linked data representation of infrastructure data, socio-demographic data, areal attributes like demand, and models describing power systems. The knowledge graph links the data with a hierarchical representation of administrative regions, supporting geospatial queries to retrieve information about the population within the vicinity of a power plant, the number of power plants, total generation capacity, and demand within specific areas. Computational agents were developed to operate on the knowledge graph. The agents performed tasks including data uploading, updating, retrieval, processing, model construction and scenario analysis. A derived information framework was used to track the provenance of information calculated by agents involved in each scenario. The knowledge graph was populated with data describing the UK power system. Two alternative models of the transmission grid with different levels of structural resolution were instantiated, providing the foundation for the power system simulation and optimisation tasks performed by the agents. The application of the dynamic knowledge graph was demonstrated via a case study that investigates clean energy transition trajectories based on the deployment of Small Modular Reactors in the UK.

Learning Crowd Motion Dynamics with Crowds

Reinforcement Learning (RL) has become a popular framework for learning desired behaviors for computational agents in graphics and games. In a multi-agent crowd, one major goal is for agents to avoid collisions while navigating in a dynamic environment. Another goal is to simulate natural-looking crowds, which is difficult to define due to the ambiguity as to what is a natural crowd motion. We introduce a novel methodology for simulating crowds, which learns most-preferred crowd simulation behaviors from crowd-sourced votes via Bayesian optimization. Our method uses deep reinforcement learning for simulating crowds, where crowdsourcing is used to select policy hyper-parameters. Training agents with such parameters results in a crowd simulation that is preferred to users. We demonstrate our method's robustness in multiple scenarios and metrics, where we show it is superior compared to alternate policies and prior work.

Use of multi-agent systems and the Internet of Things to monitor the environment of commercial broiler poultry houses through specific air enthalpy

The intensive production system for broilers requires the availability of an environment (aviary) that promotes an artificial microclimate that favors both animal well-being and productive performance; therefore, monitoring this environment is critical for production success, especially in tropical countries. This criticality opens up a range of research opportunities for monitoring because of the currently available technologies, especially in the areas of the Internet of Things and Expert Systems. Thus, this study presents a proposal for the environmental monitoring of an aviary using an Internet of Things technological apparatus combined with multi-agent systems to monitor climatic variables with the guidance of thermal comfort indicators. The experiment took place in a Cobb broiler aviary located in the countryside of the State of São Paulo, Brazil. With this objective in mind, the production period of Cobb broilers was analyzed through the construction of an Internet of Things system to collect air temperature, relative humidity, and atmospheric pressure variables combined with a data transfer mechanism for cloud recording. These variables were then analyzed by computational agents using the Java programming language with the Jade framework, which generated animal comfort indicators. The results showed that real-time monitoring of environmental variables is possible with the combination of the Internet of Things with agents that can determine animal comfort conditions according to the specific enthalpy of the air through the orchestration of a deliberative agent and with the participation of several reactive agents.

Causal Effects of High Stress Assessed Via Interviews on Mental and Physical Health: Toward Computer Agent-Driven Stress Assessment.

This study investigated the causal effect of high stress assessment via an interview on the mental and physical health of workers 1 month later. Stress assessment interviews and feedback were conducted with 50 Japanese workers. In addition to the interviewer, two occupational health professionals assessed participants' stress based on recordings. The average treatment effect was estimated by propensity score matching. High stress, according to the interview-based assessment, had a significant negative causal effect on self-reported well-being 1 month later (95% confidence interval: -3.02, -1.10). In addition, no effect of high stress on stress load, mental and physical symptoms, or burnout was observed. This study provides important insights into the prognosis of individuals who were assessed through interviews to have high stress. The findings are expected to help automate stress assessments using computer agents.

A Network Model for Modulating Sensory Processing Sensitivity in Autism Spectrum Disorder: Epigenetics, Adaptivity, and Other Factors

Autism spectrum disorder (ASD) is a neurodevelopmental condition that can significantly affect an individual's behaviour and social interactions. Comprehending how various factors may influence these behaviours is vital for devising innovative intervention strategies to assist individuals with ASD. This study presents a computational agent model designed to investigate sensory processing sensitivity (SPS) and behavioural responses to stimuli in individuals with ASD. The model incorporates feedback loops to represent the diverse and adaptive behavioural responses observed in these individuals, illustrating the impact of various factors on these behaviours. We specifically explore how epigenetic mechanisms—modifications in gene expression influenced by environmental factors—affect SPS and responsiveness to subtle sensory stimuli in ASD. To evaluate our model and showcase its effectiveness in replicating and predicting the variability in behavioural responses among individuals with ASD, we conducted simulation experiments to reproduce scenarios depicting different responses to visual stimuli. The results highlight the potential of computational models in understanding the intricate sensory experiences in ASD and offer new perspectives for future research and interventions.

Context-aware composition of agent policies by Markov decision process entity embeddings and agent ensembles

Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means that agents operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to perform services and carry out activities satisfactorily, i.e. in a goal-oriented manner, agents require prior knowledge and therefore have to develop and pursue context-dependent policies. The problem here is that prescribing policies in advance is limited and inflexible, especially in dynamically changing environments. Moreover, the context (i.e. the external and internal state) of an agent determines its choice of actions. Since the environments in which agents operate can be stochastic and complex in terms of the number of states and feasible actions, activities are usually modelled in a simplified way by Markov decision processes so that, for example, agents with reinforcement learning are able to learn policies, i.e. state-action pairs, that help to capture the context and act accordingly to optimally perform activities. However, training policies for all possible contexts using reinforcement learning is time-consuming. A requirement and challenge for agents is to learn strategies quickly and respond immediately in cross-context environments and applications, e.g., the Internet, service robotics, cyber-physical systems. In this work, we propose a novel simulation-based approach that enables a) the representation of heterogeneous contexts through knowledge graphs and entity embeddings and b) the context-aware composition of policies on demand by ensembles of agents running in parallel. The evaluation we conducted with the “Virtual Home” dataset indicates that agents with a need to switch seamlessly between different contexts, e.g. in a home environment, can request on-demand composed policies that lead to the successful completion of context-appropriate activities without having to learn these policies in lengthy training steps and episodes, in contrast to agents that use reinforcement learning. The presented approach enables both context-aware and cross-context applicability of untrained computational agents. Furthermore, the source code of the approach as well as the generated data, i.e. the trained embeddings and the semantic representation of domestic activities, is open source and openly accessible on Github and Figshare.

(Mal)adaptive Mentalizing in the Cognitive Hierarchy, and Its Link to Paranoia.

Interacting competitively requires vigilance to avoid deception. However, excessive caution can have adverse effects, stemming from false beliefs of intentional harm. So far there is no formal cognitive account of what may cause this suspiciousness. Here we present an examination of this phenomenon through the lens of Theory of Mind - the cognitive ability to consider the beliefs, intentions, and desires of others. By simulating interacting computer agents we illustrate how well-aligned agents can give rise to successful deception and justified skepticism. Crucially, we also reveal that overly cautious agents develop false beliefs that an ingenuous partner is attempting malicious trickery, leading to tangible losses. As well as formally defining a plausible mechanism for suspiciousness, paranoia, and conspiratorial thinking, our theory indicates that rather than a deficit in Theory of Mind, paranoia may involve an over-application of strategy to genuine behaviour.

Reference Chatbots in Canadian Academic Libraries

Chatbots are “computer agents that can interact with the user” in a way that feels like human-to-human conversation. While the use of chatbots for reference service in academic libraries is a topic of interest for both library professionals and researchers, little is known about how they are used in library reference service, especially in academic libraries in Canada. This article aims to fill this gap by conducting a web-based survey of 106 academic library websites in Canada and analyzing the prevalence and characteristics of chatbot and live chat services offered by these libraries. The authors found that only two libraries were using chatbots for reference service. For live chat services, the authors found that 78 libraries provided this service. The article discusses possible reasons for the low adoption of chatbots in academic libraries, such as accessibility, privacy, cost, and professional identity issues. The article also provides a case study of the authors’ institution, the University of Calgary, which integrated a chatbot service in 2021. The article concludes with suggestions for future research on chatbot use in libraries.

Spatial unity for the apperception engine

We develop a logical approach for computational agents to spatially explore their environment, extending on the Kant-inspired logical unification methods of the Apperception Engine. Evaluating models of the Regional Connection Calculus as Alexandroff Topologies, we axiomatise connectedness and unity of space. We further define dimensionality for tolerance spaces and prove that locally verifiable properties guarantee global consistency of space as the existence of isomorphisms to grids, turbands or tori. Finally, we provide a generally competent and explainable computational agent that unifies intuition in space, the Spatial Apperception Engine.

Computational Thinking and Notional Machines: The Missing Link

In learning to program and understanding how a programming language controls a computer, learners develop both insights and misconceptions whilst their mental models are gradually refined. It is important that the learner is able to distinguish the different elements and roles of a computer (compiler, interpreter, memory, etc.), which novice programmers may find difficult to comprehend. Forming accurate mental models is one of the potential sources of difficulty inextricably linked to mastering computing concepts and processes, and for learning computer programming. It is common to use some form of representation (e.g., an abstract machine or a Computational Agent (CA)) to support technical or pedagogic explanations. The Notional Machine (NM) is a pedagogical device that entails one or more computational concepts, originally described as an idealised computer operating with the constructs of a particular programming language. It can be used to support specific or general learning goals and will typically have some concrete representation that can be referred to. Computational Thinking (CT), which is defined as a way of thinking that is used for [computational] problem solving, is often presented as using a CA to carry out information processing presented by a solution. In CT, where the typical goal is to produce an algorithm or a computer program, the CA seemingly serves a purpose very similar to an NM. Although it changes through the different stages of development (of the learner and of the curriculum), the roles of CAs and NMs can be seen as versatile tools that connect a learner’s mental model with the conceptual model of a program. In this article, we look at this relationship between CAs and NMs, and indicate how they would look at different stages of learning. We traverse the range of definitions and usages of these concepts, and articulate models that clarify how these are viewed in the literature. This includes exploring the nature of machines and agents, and how historical views of these relate to modern pedagogy for computation. We argue that the CA can be seen as an abstract, simplified variant of an NM that provides a useful perspective to the learner to support them to form robust mental models of NMs more efficiently and effectively. We propose that teaching programming should make use of the idea of a CA at different stages of learning, as a link that connects a learner’s mental model to a full NM.

Development of a Virtual Human for Supporting Tobacco Cessation During the COVID-19 Pandemic.

People who consume tobacco are at greater risk of developing severe COVID-19. Unfortunately, the COVID-19 pandemic reduced the accessibility of tobacco cessation services as a result of necessary social restrictions. Innovations were urgently needed to support tobacco cessation during the pandemic. Virtual humans are artificially intelligent computer agents with a realistic, humanlike appearance. Virtual humans could be a scalable and engaging way to deliver tobacco cessation information and support. Florence, a virtual human health worker, was developed in collaboration with the World Health Organization to remotely support people toward tobacco cessation during the COVID-19 pandemic. Florence delivers evidence-based information, assists with making quit plans, and directs people to World Health Organization-recommended cessation services in their country. In this viewpoint, we describe the process of developing Florence. The development was influenced by a formative evaluation of data from 115 early users of Florence from 49 countries. In general, Florence was positively perceived; however, changes were requested to aspects of her design and content. In addition, areas for new content were identified (eg, for nonsmoker support persons). Virtual health workers could expand the reach of evidence-based tobacco cessation information and personalized support. However, as they are a new innovation in tobacco cessation, their efficacy, feasibility, and acceptability in this application needs to be evaluated, including in diverse populations.

Understanding Human-Autonomy Teams Through a Human-Animal Teaming Model.

The relationship between humans and animals is complex and influenced by multiple variables. Humans display a remarkably flexible and rich array of social competencies, demonstrating the ability to interpret, predict, and react appropriately to the behavior of others, as well as to engage others in a variety of complex social interactions. Developing computational systems that have similar social abilities is a critical step in designing robots, animated characters, and other computer agents that appear intelligent and capable in their interactions with humans and each other. Further, it will improve their ability to cooperate with people as capable partners, learn from natural instruction, and provide intuitive and engaging interactions for human partners. Thus, human-animal team analogs can be one means through which to foster veridical mental models of robots that provide a more accurate representation of their near-future capabilities. Some digital twins of human-animal teams currently exist but are often incomplete. Therefore, this article focuses on issues within and surrounding the current models of human-animal teams, previous research surrounding this connection, and the challenges when using such an analogy for human-autonomy teams.

Behavioral patterns in collaborative problem solving: a latent profile analysis based on response times and actions in PISA 2015

Process data are becoming more and more popular in education research. In the field of computer-based assessments of collaborative problem solving (ColPS), process data have been used to identify students’ test-taking strategies while working on the assessment, and such data can be used to complement data collected on accuracy and overall performance. Such information can be used to understand, for example, whether students are able to use a range of styles and strategies to solve different problems, given evidence that such cognitive flexibility may be important in labor markets and societies. In addition, process information might help researchers better identify the determinants of poor performance and interventions that can help students succeed. However, this line of research, particularly research that uses these data to profile students, is still in its infancy and has mostly been centered on small- to medium-scale collaboration settings between people (i.e., the human-to-human approach). There are only a few studies involving large-scale assessments of ColPS between a respondent and computer agents (i.e., the human-to-agent approach), where problem spaces are more standardized and fewer biases and confounds exist. In this study, we investigated students’ ColPS behavioral patterns using latent profile analyses (LPA) based on two types of process data (i.e., response times and the number of actions) collected from the Program for International Student Assessment (PISA) 2015 ColPS assessment, a large-scale international assessment of the human-to-agent approach. Analyses were conducted on test-takers who: (a) were administered the assessment in English and (b) were assigned the Xandar unit at the beginning of the test. The total sample size was N = 2,520. Analyses revealed two profiles (i.e., Profile 1 [95%] vs. Profile 2 [5%]) showing different behavioral characteristics across the four parts of the assessment unit. Significant differences were also found in overall performance between the profiles.