{"title":"Constructivist procedural learning for grounded cognitive agents","authors":"Sean Kugele","doi":"10.1016/j.cogsys.2025.101321","DOIUrl":"10.1016/j.cogsys.2025.101321","url":null,"abstract":"<div><div>Constructivism is a learning theory based on the idea that individuals actively build their understanding of the world through their interactions with their environment. Learning is a dynamic process where new knowledge builds on prior knowledge, and a learner’s mental models are continually refined by their experiences. Building on this theoretical framework and Drescher’s seminal contributions to constructivist AI, this paper explores constructivism within the context of LIDA (Learning Intelligent Decision Agent), a biologically inspired cognitive architecture. Specifically, I develop a modified version of Drescher’s schema mechanism, which I use to implement LIDA’s Procedural Memory and Action Selection modules. I demonstrate that an agent based on this implementation can construct an accurate internal model of its environmental interactions and use that model to select goal-directed behaviors. This work significantly advances LIDA’s computational capabilities by implementing grounded instructionist procedural learning, hierarchical action plans, and the selection of exploratory behaviors. These computational enhancements will enable the creation of more sophisticated LIDA-based agents that can operate in more complex environments where the hand-coding of procedural knowledge is infeasible. An alternate way to view this work is as an enhancement to Drescher’s schema mechanism, which is a purely symbolic and ungrounded cognitive system. LIDA’s sensory and perceptual systems provide a means by which the schema mechanism’s representations can be grounded. This, in itself, is an important contribution of this paper.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101321"},"PeriodicalIF":2.1,"publicationDate":"2025-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Self-control on the path toward artificial moral agency","authors":"Paul Bello, Will Bridewell","doi":"10.1016/j.cogsys.2024.101316","DOIUrl":"10.1016/j.cogsys.2024.101316","url":null,"abstract":"<div><div>The ability of agents to commit to their plans and see them through is a core concept in the philosophy of action (<span><span>Bratman, 1987</span></span>, <span><span>Holton, 2009</span></span>) and is considered to be a defining feature of having an intention. Seeing plans through in the face of highly compelling opportunities for action that are incompatible with our current commitments requires self-control. In this review paper, we draw upon ancient and modern literature on self-control along with contemporary ideas about the cognitive architecture supporting intentional action to argue that any computational account of moral agency must include an approach to self-control. In addition, we extract and develop a list of necessary features of the phenomena against which individual modeling efforts can be compared. The ARCADIA cognitive system will be discussed in light of this list of features and used to demonstrate both success and failure in a highly simplified self-control dilemma. Finally, we end by discussing a path toward more functionally complete models of agency and control, along with offering perfunctory thoughts on some of the more conceptually challenging issues to address in the future.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101316"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Artemiy A. Kotov , Alexander A. Filatov , Zakhar A. Nosovets
{"title":"Cognitive architecture for F-2 companion robot to support semantic shifts and cognitive domains via scenario oppositions","authors":"Artemiy A. Kotov , Alexander A. Filatov , Zakhar A. Nosovets","doi":"10.1016/j.cogsys.2024.101320","DOIUrl":"10.1016/j.cogsys.2024.101320","url":null,"abstract":"<div><div>We develop an applied cognitive architecture, which can operate on companion robots and support cognitive functions typical of higher order human communication, such as humor and cognitive domains like <em>imagination</em>, irony and <em>theory of mind</em>. In the applied studies this architecture, developed as a real-world interface for the cognitive model, operates on F-2 companion robot or runs text processing on the server without the robot. The robot constructs representation for speech, visual and tactile events in a unified way, based on the semantics representations. To simulate cognitive domains and humor, we implement parallel processing of speech syntax and semantics, so that a meaning for an alternative syntactic tree (homonymy) can be used for a humorous utterance. The parallel processing is implemented via an engine of scenarios – <em>if-then</em> operators or <em>productions</em>. The scenarios, invoked by a stimulus, compete with each other basing on the oppositions of their semantic markers. The winning scenario forms a “believable” representation of a stimulus for the robot, while the suppressed (opposed) scenarios form the representations of cognitive domains. If a stimulus is evaluated as “bad”, but an opposed scenario suggests “good” representation, this representation is used for <em>imagination</em>. If a scenario suggests an emotional interpretation and assigns “me/myself” marker, while the correct representation suggests “another” person in this position, this representation is used for <em>the theory of mind</em> – another person’s point of view. Scenarios, departing from a stimulus, are also used as an inference engine that forms derived semantic representations to be replied by the robot. This mechanism is also combined with emotional evaluation, as a rational inference may invoke emotions or shift the category of an object in the initial stimulus.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101320"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Konstantina Zacharaki, Queralt Prat-i-Pubill, Jennifer Nguyen, Nil Agell, Núria Agell
{"title":"Comparing food waste interests and environmental concerns in young adults: A qualitative reasoning approach","authors":"Konstantina Zacharaki, Queralt Prat-i-Pubill, Jennifer Nguyen, Nil Agell, Núria Agell","doi":"10.1016/j.cogsys.2024.101318","DOIUrl":"10.1016/j.cogsys.2024.101318","url":null,"abstract":"<div><div>The large amount of food waste produced worldwide highlights the urgent need to investigate this phenomenon promptly with new methods in order to reduce it. In the present work, we consider a qualitative reasoning approach in an attempt to understand people’s interest in the food waste (FW) problem. In this direction, we run an in-person taste experiment and acquire data from 310 participants. We apply a measure based on hesitant linguistic terms sets (HLTS) to capture the degree of interest towards the environment as individuals respond to the New Environmental Paradigm scale (NEP) (<span><span>Dunlap et al., 2000</span></span>). We also calculate an index of hesitancy based on participants’ responses. Previously, they had to decide on whether a piece of fruit allegedly coming from the supermarket tastes better than another one allegedly coming from an alternative source such as applications designed to reduce food waste.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101318"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexander Chernyavskiy , Alexey Skrynnik , Aleksandr Panov
{"title":"Applying opponent and environment modelling in decentralised multi-agent reinforcement learning","authors":"Alexander Chernyavskiy , Alexey Skrynnik , Aleksandr Panov","doi":"10.1016/j.cogsys.2024.101306","DOIUrl":"10.1016/j.cogsys.2024.101306","url":null,"abstract":"<div><div>Multi-agent reinforcement learning (MARL) has recently gained popularity and achieved much success in different kind of games such as zero-sum, cooperative or general-sum games. Nevertheless, the vast majority of modern algorithms assume information sharing during training and, hence, could not be utilised in decentralised applications as well as leverage high-dimensional scenarios and be applied to applications with general or sophisticated reward structure. Thus, due to collecting expenses and sparsity of data in real-world applications it becomes necessary to use world models to model the environment dynamics, using latent variables — i.e. use world model to generate synthetic data for training of MARL algorithms. Therefore, focusing on the paradigm of decentralised training and decentralised execution, we propose an extension to the model-based reinforcement learning approaches leveraging fully decentralised training with planning conditioned on neighbouring co-players’ latent representations. Our approach is inspired by the idea of opponent modelling. The method makes the agent learn in joint latent space without need to interact with the environment. We suggest the approach as proof of concept that decentralised model-based algorithms are able to emerge collective behaviour with limited communication during planning, and demonstrate its necessity on iterated matrix games and modified versions of StarCraft Multi-Agent Challenge (SMAC).</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101306"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ismail M. Gadzhiev , Alexander S. Makarov , Vadim L. Ushakov , Vyacheslav A. Orlov , Georgy A. Ivanitsky , Sergei A. Dolenko
{"title":"Creating A dynamic cognovisor – Brain activity recognition using principal Component analysis and Machine learning models","authors":"Ismail M. Gadzhiev , Alexander S. Makarov , Vadim L. Ushakov , Vyacheslav A. Orlov , Georgy A. Ivanitsky , Sergei A. Dolenko","doi":"10.1016/j.cogsys.2024.101314","DOIUrl":"10.1016/j.cogsys.2024.101314","url":null,"abstract":"<div><div>This study explores the feasibility of developing a dynamic cognovisor capable of recognizing cognitive states and transitions using fMRI data. Data were collected from 31 participants performing spatial and verbal tasks during fMRI scanning and were preprocessed using a nine-step algorithm for artifact removal and denoising. Three types of classification problems were examined, with machine learning methods and dimensionality reduction techniques applied to classify activity states. The best-performing models were identified for each classification problem, providing insights into their applicability. Notably, binary classification of resting versus active states achieved good quality with relatively simple methods. A key finding underscores the importance of accounting for temporal history of the signal prior to the prediction moment to improve model performance.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101314"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rubén Torres Agustín , Zareth Bonilla González , Mario A. Rodríguez Camacho , Sebastián Almonte , Wendy Fabiola Lara Galindo , Francisco Abelardo Robles Aguirre
{"title":"Corrigendum to “Detection of semantic inconsistencies of motor actions: From language to praxis” [Cognit. Syst. Res. 88 (2024) 1–13/101292]","authors":"Rubén Torres Agustín , Zareth Bonilla González , Mario A. Rodríguez Camacho , Sebastián Almonte , Wendy Fabiola Lara Galindo , Francisco Abelardo Robles Aguirre","doi":"10.1016/j.cogsys.2025.101323","DOIUrl":"10.1016/j.cogsys.2025.101323","url":null,"abstract":"","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101323"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mikhail Kiselev , Alexander Ivanitsky , Denis Larionov
{"title":"A purely spiking approach to reinforcement learning","authors":"Mikhail Kiselev , Alexander Ivanitsky , Denis Larionov","doi":"10.1016/j.cogsys.2024.101317","DOIUrl":"10.1016/j.cogsys.2024.101317","url":null,"abstract":"<div><div>At present, implementation of learning mechanisms in spiking neural networks (SNN) cannot be considered as a solved scientific problem despite plenty of SNN learning algorithms proposed. It is also true for SNN implementation of reinforcement learning (RL), while RL is especially important for SNNs because of its close relationship to the domains most promising from the viewpoint of SNN application such as robotics. In the present paper, an SNN structure is described which, seemingly, can be used in wide range of RL tasks. The distinctive feature of our approach is usage of only the spike forms of all signals involved — sensory input streams, output signals sent to actuators and reward/punishment signals. Besides that, selection of the neuron/plasticity models was determined by the requirement that they should be easily implemented on modern neurochips. The SNN structure considered in the paper includes spiking neurons described by a generalization of the LIFAT (leaky integrate-and-fire neuron with adaptive threshold) model and a simple spike timing dependent synaptic plasticity model (a generalization of dopamine-modulated plasticity). In this study, we use the model-free approach to RL but it is based on very general assumptions about RL task characteristics and has no visible limitations on its applicability (inside the class of model-free RL tasks). To test our SNN, we apply it to a simple but non-trivial task of training the network to keep a chaotically moving light spot in the view field of an emulated Dynamic Vision Sensor (DVS) camera. Successful solution of this RL problem can be considered as an evidence in favor of efficiency of our approach.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"89 ","pages":"Article 101317"},"PeriodicalIF":2.1,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Higher-order adaptive dynamical system modelling of epigenetic mechanisms in infant temperament shaped by prenatal maternal stress","authors":"Labiba Aziz , Jan Treur","doi":"10.1016/j.cogsys.2024.101315","DOIUrl":"10.1016/j.cogsys.2024.101315","url":null,"abstract":"<div><div>Prenatal maternal stress (PNMS) has significant implications for infant temperament, primarily through alterations in the hypothalamic–pituitary–adrenal (HPA) axis and epigenetic mechanisms. This study explores the effects of PNMS on infant stress reactivity using a fifth-order adaptive dynamical system model. The model integrates genetic, epigenetic, and environmental factors, focusing on the downregulation of 11β-HSD-2, an enzyme responsible for converting active cortisol to its inactive form, and its subsequent influence on fetal cortisol exposure. The article also employs network-oriented modeling to represent epigenetic changes and their impact on infant temperament development, emphasizing the HPA axis’ role in stress regulation. Simulation experiments compare scenarios with PNMS, illustrating the long-term developmental consequences on temperament. This research highlights the importance of maternal well-being during pregnancy in shaping infant stress responses and provides insights into the developmental origins of health and disease.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"90 ","pages":"Article 101315"},"PeriodicalIF":2.1,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143097275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Integrated model of cerebellal supervised learning and basal ganglia’s reinforcement learning for mobile robot behavioral decision-making","authors":"Zhiqiang Wu , Dongshu Wang , Lei Liu","doi":"10.1016/j.cogsys.2024.101302","DOIUrl":"10.1016/j.cogsys.2024.101302","url":null,"abstract":"<div><div>Behavioral decision-making in unknown environments of mobile robots is a crucial research topic in robotics. Inspired by the working mechanism of different brain regions in mammals, this paper designed a new hybrid model integrating the functions of cerebellum and basal ganglia by simulating the memory replay of hippocampus, so as to realize the autonomous behavioral decision-making of robot in unknown environments. A reinforcement learning module based on Actor-Critic framework and a developmental network module are used to simulate the functions of the basal ganglia and cerebellum, respectively. Considering the different functions of D1 and D2 dopamine receptors in basal ganglia, an Actor network module with separate learning of positive and negative rewards is designed for the basal ganglia to realize efficient exploration of the environments by the agent. According to the characteristics of biological memory, a physiological memory priority index is designed for hippocampus memory replay, which improves the offline learning efficiency of cerebellum. The integrated model enables dynamic switching between decisions made by cerebellum and basal ganglia based on the agent’s cognitive level with respect to the environment. Finally, the effectiveness of the proposed model is verified through experiments on agent navigation in both simulation and real environments, as well as through performance comparison experiments with other learning algorithms.</div></div>","PeriodicalId":55242,"journal":{"name":"Cognitive Systems Research","volume":"88 ","pages":"Article 101302"},"PeriodicalIF":2.1,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}