Solve Complex Tasks Research Articles

Chemical Species Ontology for Data Integration and Knowledge Discovery.

Web ontologies are important tools in modern scientific research because they provide a standardized way to represent and manage web-scale amounts of complex data. In chemistry, a semantic database for chemical species is indispensable for its ability to interrelate and infer relationships, enabling a more precise analysis and prediction of chemical behavior. This paper presents OntoSpecies, a web ontology designed to represent chemical species and their properties. The ontology serves as a core component of The World Avatar knowledge graph chemistry domain and includes a wide range of identifiers, chemical and physical properties, chemical classifications and applications, and spectral information associated with each species. The ontology includes provenance and attribution metadata, ensuring the reliability and traceability of data. Most of the information about chemical species are sourced from PubChem and ChEBI data on the respective compound Web pages using a software agent, making OntoSpecies a comprehensive semantic database of chemical species able to solve novel types of problems in the field. Access to this reliable source of chemical data is provided through a SPARQL end point. The paper presents example use cases to demonstrate the contribution of OntoSpecies in solving complex tasks that require integrated semantically searchable chemical data. The approach presented in this paper represents a significant advancement in the field of chemical data management, offering a powerful tool for representing, navigating, and analyzing chemical information to support scientific research.

Storytelling as a tool for forming and supporting organisational culture in medical institutions

The article discusses the role and importance of storytelling in the context of creating and maintaining organisational culture in the healthcare sector. Medical institutions are constantly solving complex tasks related to the provision of high-quality medical care and interaction with patients and staff. In this regard, storytelling is an important tool, aimed at strengthening cultural values and adjusting goals.
 The study examines the nature of organisational culture, its main components and culture, its main components and the peculiarities of its formation and maintenance in medical institutions. Organisational culture affects all aspects of business processes and is an important element of corporate identity, in particular in the healthcare sector. healthcare.
 The authors determine that storytelling as a communication tool has become an important part of business communication and management in recent decades part of business communication and management practice in recent decades. Storytelling can be used to form common values and create meaningful narratives that promote cultural change and support the organisational organisational identity of healthcare facilities.
 Stories in healthcare facilities reveal the specifics and uniqueness of the organisation, help to distinguish it from competitors from competitors and create a competitive advantage in the market. They form the organisation’s identity and the loyalty of employees and customers. Storytelling has an impact on on the organisational culture of a medical institution, promotes stability and highlights the unique character of the organisation character of the organisation; it allows to form values, beliefs and needs of of employees based on the institution’s mission. Storytelling is important for understanding medical discourse and the system of narratives in healthcare organisations. It supports or discredits official narratives or discredit them, depending on the perception of stakeholders. It is important that storytelling in healthcare facilities is accessible to all stakeholders and promote internal identification and loyalty to the institution.
 Thus, storytelling is an essential tool for building and maintaining organisational culture in healthcare facilities, helping to create a unique identity and competitive advantage.
 The article aims to stimulating discussion of the experience of using storytelling and further research of this important aspect of management in the healthcare sector. of healthcare enterprises.

Artificial Intelligence and Machine Learning in Rotator Cuff Tears

Rotator cuff tears (RCTs) negatively impacts patient well-being. Artificial intelligence (AI) is emerging as a promising tool in medical decision-making. Within AI, deep learning allows to autonomously solve complex tasks. This review assesses the current and potential applications of AI in the management of RCT, focusing on diagnostic utility, challenges, and future perspectives. AI demonstrates promise in RCT diagnosis, aiding clinicians in interpreting complex imaging data. Deep learning frameworks, particularly convoluted neural networks architectures, exhibit remarkable diagnostic accuracy in detecting RCTs on magnetic resonance imaging. Advanced segmentation algorithms improve anatomic visualization and surgical planning. AI-assisted radiograph interpretation proves effective in ruling out full-thickness tears. Machine learning models predict RCT diagnosis and postoperative outcomes, enhancing personalized patient care. Challenges include small data sets and classification complexities, especially for partial thickness tears. Current applications of AI in RCT management are promising yet experimental. The potential of AI to revolutionize personalized, efficient, and accurate care for RCT patients is evident. The integration of AI with clinical expertise holds potential to redefine treatment strategies and optimize patient outcomes. Further research, larger data sets, and collaborative efforts are essential to unlock the transformative impact of AI in orthopedic surgery and RCT management.

The effects of group adaptation on task performance: An agent-based approach.

Organisations rely upon group formation to solve complex tasks, and groups often adapt to the demands of the task they face by changing their composition periodically. Previous research has often employed experimental, survey-based, and fieldwork methods to study the effects of group adaptation on task performance. This paper, by contrast, employs an agent-based approach to study these effects. There are three reasons why we do so. First, agent-based modelling and simulation allows to take into account further factors that might moderate the relationship between group adaptation and task performance, such as individual learning and task complexity. Second, such an approach allows to study large variations in the variables of interest, which contributes to the generalisation of our results. Finally, by employing an agent-based approach, we are able to study the longitudinal effects of group adaptation on task performance. Longitudinal analyses are often missing in prior related research. Our results indicate that reorganising well-performing groups might be beneficial, but only if individual learning is restricted. However, there are also cases in which group adaptation might unfold adverse effects. We provide extensive analyses that shed additional light on and help explain the ambiguous results of previous research.

MURM: Utilization of Multi-Views for Goal-Conditioned Reinforcement Learning in Robotic Manipulation

We present a novel framework, multi-view unified reinforcement learning for robotic manipulation (MURM), which efficiently utilizes multiple camera views to train a goal-conditioned policy for a robot to perform complex tasks. The MURM framework consists of three main phases: (i) demo collection from an expert, (ii) representation learning, and (iii) offline reinforcement learning. In the demo collection phase, we design a scripted expert policy that uses privileged information, such as Cartesian coordinates of a target and goal, to solve the tasks. We add noise to the expert policy to provide sufficient interactive information about the environment, as well as suboptimal behavioral trajectories. We designed three tasks in a Pybullet simulation environment, including placing an object in a desired goal position and picking up various objects that are randomly positioned in the environment. In the representation learning phase, we use a vector-quantized variational autoencoder (VQVAE) to learn a more structured latent representation that makes it feasible to train for RL compared to high-dimensional raw images. We train VQVAE models for each distinct camera view and define the best viewpoint settings for training. In the offline reinforcement learning phase, we use the Implicit Q-learning (IQL) algorithm as our baseline and introduce a separated Q-functions method and dropout method that can be implemented in multi-view settings to train the goal-conditioned policy with supervised goal images. We conduct experiments in simulation and show that the single-view baseline fails to solve complex tasks, whereas MURM is successful.

Performance of Large Language Models (ChatGPT, Bing Search, and Google Bard) in Solving Case Vignettes in Physiology.

Background Large language models (LLMs) have emerged as powerful tools capable of processing and generating human-like text. These LLMs, such as ChatGPT (OpenAI Incorporated, Mission District, San Francisco, United States), Google Bard (Alphabet Inc., CA, US),and Microsoft Bing (Microsoft Corporation, WA, US), have been applied across various domains, demonstrating their potential to assist in solving complex tasks and improving information accessibility. However, their application in solving casevignettes in physiology has not been explored. This study aimed to assess the performance of three LLMs, namely, ChatGPT (3.5; free research version), Google Bard (Experiment), and Microsoft Bing (precise), in answering cases vignettes in Physiology. Methods This cross-sectional study was conducted in July 2023. A total of 77 case vignettes in physiology were prepared by two physiologists and were validated by two other content experts. These cases were presented to each LLM, and their responses were collected. Two physiologists independently rated the answers provided by the LLMs based on their accuracy. The ratings were measured on a scale from 0 to 4 according to the structure of the observed learning outcome (pre-structural = 0, uni-structural = 1, multi-structural = 2, relational = 3, extended-abstract). The scores among the LLMs were compared by Friedman's test and inter-observer agreement was checked by the intraclass correlation coefficient (ICC). Results The overall scores for ChatGPT, Bing, and Bard in the study, with a total of 77 cases, were found to be 3.19±0.3, 2.15±0.6, and 2.91±0.5, respectively, p<0.0001. Hence, ChatGPT 3.5 (free version) obtained the highest score, Bing (Precise) had the lowest score, and Bard (Experiment) fell in between the two in terms of performance. The average ICC values for ChatGPT, Bing, and Bard were 0.858 (95% CI: 0.777 to 0.91, p<0.0001), 0.975 (95% CI: 0.961 to 0.984, p<0.0001), and 0.964 (95% CI: 0.944 to 0.977, p<0.0001), respectively. Conclusion ChatGPT outperformed Bard and Bing in answering case vignettes in physiology. Hence, students and teachers may think about choosing LLMs for their educational purposes accordingly for case-based learning in physiology. Further exploration of their capabilities is needed for adopting those in medical education and support for clinical decision-making.

On the question of the electronic parliament essence: the ukrainian dimension

In view of the expediency and demand for the most effective ways to solve the challenges of globalization information processes, the determination of the foreign policy vector of our country's development in the direction of European and Euro-Atlantic integration, the need for high-quality modern tools for solving complex tasks faced by public authorities, Ukraine has determined the strategic development of electronic democracy and state policy of digital transformation of society. The article focuses attention on the main conceptual idea of e-democracy – the involvement of the public in the political processes of state formation, state administration, and local government through the wide application of information and communication technologies in democratic processes. certain topical problems of the implementation of the electronic parliament in Ukraine are clarified. It is emphasized that the e-parliament is among the strategically determined main components of the domestic process of establishing and developing electronic democracy. The relevance of the issue is primarily related to the expediency of a comprehensive constitutional and legal analysis of the activities of the Verkhovna Rada of Ukraine –the Parliament of Ukraine in the context of the introduction of forms and means of e-democracy, the implementation of digital transformation of state and social life, challenges and threats of today in the conditions of martial law for the development of Ukrainian parliamentarism as a whole. It is emphasized that the concept of e-parliament has become widespread, and the construction of such an institution has become an important trend in the development of modern world parliaments. The international legal principles of the studied phenomenon are analyzed from the point of view of its practical value and definition of the concept, essence. It was concluded that during the entire period of the existence of the Verkhovna Rada of Ukraine as a parliament, the only body of legislative power, the foundations of the development of the "e-parliament" were also laid (introduction and use ofmodern forms of ICT, information content of web resources, information support of various parliamentary activities, etc). After Ukraine's accession to the Declaration of the Open Parliament (2016), the intensity of the relevant processes is increasing. Emphasis is made on the fact that efforts to implement plans for the development of electronic parliamentarism are primarily aimed at improving the quality of the lawmaking process and the effective interaction of all its subjects and participants. Attention is payed to the fact that domestic constitutional and legal science has not yet formed a generally accepted concept of e-parliament as a legal category, a unified approach to understanding its essence, content. Various approaches to defining the concept, essence, content of the electronic parliament in the domestic literature are studied. Determining the essence of the definition, scientists consider it mainly from the point of view of technological aspects,the use of ICT in parliamentary activities. The author's definition of "E-parliament" is provided – it is information and communication, digital technologies for the implementation of parliamentary activities, the electronic infrastructure of the parliament, a condition for ensuring its open, transparent, accountable to voters functioning, expanding the development opportunities and strengthening democratic institutions, citizen participation in political processes. It is emphasized that the electronic parliament cannot be considered as a separate type of traditional democratic parliament, as well as the fact that it cannot be completely identified with the constitutionally defined parliament of Ukraine The conformity of the practical activities of the Verkhovna Rada of Ukraine with the concept of e-parliament is clarified. Key words: government reform, e-democracy, digital, form, mean, stools,information and communication technologies, e-parliament, e-parliamentarism, Declaration of the Open Parliament, Verkhovna Rada of Ukraine

Robot task programming in complex task scenarios based on spatio-temporal constraint calculus

PurposeRobots face fundamental challenges in achieving reliable and stable operations for complex home service scenarios. This is one of the crucial topics of robotics methods to imitate human beings’ advanced cognitive characteristics and apply them to solve complex tasks. The purpose of this study is to enable robots to have the ability to understand the scene and task process in complex scenes and to provide a reference method for robot task programming in complex scenes.Design/methodology/approachThis paper constructs a task modeling method for robots in complex environments based on the characteristics of the perception-motor memory model of human cognition. In the aspect of episodic memory construction, the task execution process is included in the category of qualitative spatio-temporal calculus. The topology interaction of objects in a task scenario is used to define scene attributes. The task process can be regarded as changing scene attributes on a time scale. The qualitative spatio-temporal activity graphs are used to analyze the change process of the object state with time during the robot task execution. The tasks are divided according to the different values of scene attributes at different times during task execution. Based on this, in procedural memory, an object-centered motion model is developed by analyzing the changes in the relationship between objects in the scene episode by analyzing the scene changes before and after the robot performs the actions. Finally, the task execution process of the robot is constructed by alternately reconstructing episodic memory and procedural memory.FindingsTo verify the applicability of the proposed model, a scenario where the robot combines the object (one of the most common tasks in-home service) is set up. The proposed method can obtain the landscape of robot tasks in a complex environment.Originality/valueThe robot can achieve high-level task programming through the alternating interpretation of scenarios and actions. The proposed model differs from traditional methods based on geometric or physical feature information. However, it focuses on the spatial relationship of objects, which is more similar to the cognitive mechanism of human understanding of the environment.

HCS-R-HER: Hierarchical reinforcement learning based on cross subtasks rainbow hindsight experience replay

Sparse reward feedback from the environment is the main challenge for learning goal-oriented tasks based on reinforcement learning. The lack of sufficient exploration also leads to the inability of the agent to robustly learn strategies, especially for hierarchical task control of continuous action space continuum robots, which are more difficult to explore. In this paper, we propose a hierarchical reinforcement learning framework, HCS-R-HER, to accelerate learning by reusing empirical data across subtasks. It uses an upper-level controller, meta-controller, to integrate the underlying targets, and a set of lower-level controllers, controllers, responsible for performing atomic operations. The Oracle perspective mechanism can skip the process of unfinished subtasks, which helps speed up the learning of the meta-controller. The CS-R-HER framework is used to improve the sparsity of the data and accelerate the learning of controllers. Our approach can solve complex tasks or hierarchical tasks more effectively, especially for continuum robot motion environments in continuous action space. Our method is the first time to apply HER to data augmentation for hierarchical tasks and to implement a framework where multiple subgoals are learned together.

Genetic Algorithm-Based Task Assignment for Fleet of Unmanned Surface Vehicles in Dynamically Changing Environment

Unmanned vehicles are gaining the attention of professional operators and the general public. The implementation of unmanned vehicles is evident in, among other fields, emergency management, agriculture, traffic monitoring, post-disaster operations, and delivery of goods. Naturally, a group of unmanned vehicles can cooperatively complete operations more proficiently than a single vehicle. However, several issues must be resolved before a stable and reliable group of unmanned vehicles can be generally deployed to solve tasks in civil infrastructures and in industrial facilities. Here, a framework for the guidance of a fleet of unmanned surface vehicles is proposed. The framework utilizes several levels of control, namely Global Planning Level, Local Planning Level, and Low-Level Control. While the individual vehicles are completely autonomous in their operational locomotion and obstacle avoidance (low-level control and local planning), the task assignment for each vehicle (or group of them) is provided by a global planning process, based on the genetic algorithm. The framework provides a concept to solve complex tasks for the fleet of unmanned surface vehicles (USVs). This includes, but is not necessarily limited to, a dynamically changing environment, different types of USVs with special abilities, multiple types of areal restrictions and obstacles, different restrictions for individual USVs, cooperation of multiple USVs to solve their subtasks, energy consumption optimization, etc. The framework can be advantageously applied to tasks such as warehouse logistics, surface maintenance, area exploration, etc. At the end of the study, the application of the framework is presented using a simulated example of cooperative problem solving using six vehicles.

Conceptual development from the perspective of a brain-inspired robotic architecture

Concepts are central to reasoning and intelligent behaviour. Scientific evidence shows that conceptual development is fundamental for the emergence of high-cognitive phenomena. Here, we model such phenomena in a brain-inspired cognitive robotic model and examine how the robot can learn, categorise, and abstract concepts to voluntary control behaviour. The paper argues that such competence arises with sufficient conceptual content from physical and social experience. Hence, senses, motor abilities and language, all contribute to a robot’s intelligent behaviour. To this aim, we devised a method for attaining concepts, which computationally reproduces the steps of the inductive thinking strategy of the Concept Attainment Model (CAM). Initially, the robot is tutor-guided through socio-centric cues to attain concepts and is then tested consistently to use these concepts to solve complex tasks. We demonstrate how the robot uses language to create new categories by abstraction in response to human language-directed instructions. Linguistic stimuli also change the representations of the robot’s experiences and generate more complex representations for further concepts. Most notably, this work shows that this competence emerges from the robot’s ability to understand the concepts similarly to human understanding. Such understanding was also maintained when concepts were expressed in multilingual lexicalisations showing that labels represent concepts that allowed the model to adapt to unfamiliar contingencies in which it did not have directly related experiences. The work concludes that language is an essential component of conceptual development, which scaffolds the cognitive continuum of a robot from low-to-high cognitive skills, including its skill to understand.

FORMATION OF ADOLESCENTS’ SOCIAL COMPETENCE IN EDUCATIONAL INSTITUTION ENVIRONMENT

The study is devoted to the actual problem of the formation of social competence of adolescents. The aim of the research is to present the theoretical essence of the social competence and try the method of forming the social competence of teenagers out in practice. It is stated that the formation of the personal social competence is one of the key tasks of the present-day school due to the main school documents and the guidelines for the schoolchildren education in educational institutions. It is justified that social competence is an acquired skill that can be formed and developed throughout the person’s life. The developed social competence determines the status of an individual in society and affects personal success in further professional activities.In the study, the social competence is presented as universal personal qualities, knowledge, skills, behavioural models, which are required for person’s successful socialization. The key features of social competence are: 1) recognition of the person’s value-motivational sphere; 2) readiness to solve complex tasks (state of internal psychological mobilization); 3) persistence of the manifestation of this quality. It was found that important components of social competence for today’s adolescence are: the ability to find constructive models of behaviour in various problem situations; navigate in the information space; apply the acquired theoretical knowledge in practice; the ability to work in groups, to cooperate with peers and older people; the ability to resolve productively conflict situations, based on the understanding of mental, ethnic, and cultural characteristics of different social strata of the population; the ability to conduct business electronic correspondence with various recipients, etc.Diagnostics for determining the manifestation of social competence of schoolchildren is presented, which is based on Doll’s theory of social competence. The study describes the method of forming the social competence of teenagers by means of the case method. The didactic requirements for the use of the case method in order to form the researched quality are revealed, namely: saturation of the content of the cases with a meta-subject social context, multi-problems; connection of tasks with life priorities, interests, values of teenagers; the use of cases, that involves a combination of curricular and extracurricular activities, actualization of interdisciplinary knowledge, social experience of students; use of cases based on group work; implementation of the principle of cooperation in the process of solving cases, performance by the teacher of the role of moderator.

Modern approaches to the introduction of higher education degrees for the speciality 226 Pharmacy, industrial pharmacy

The main direction of the development of the education system in Ukraine is the introduction of European standards, technologies, norms, and perspectives to ensure competitiveness in the market of European education services.&#x0D; The study aimed to highlight modern approaches to the standardization of higher education in the context of shaping professional competences of future pharmacists, to identify peculiarities and possibilities of applying a systemic approach to the development of a higher education standard for the specialty of 226 Pharmacy, Industrial Pharmacy of the second (master’s) level.&#x0D; The research materials consisted of references containing information on the development, approval, and implementation of higher education standard. The following methods were used in the study: synthetic, analytical, information search, descriptive, and generalization.&#x0D; The pharmaceutical industry is socially significant, and the specialty of 226 Pharmacy, Industrial Pharmacy, as well as all the specialties in the field of study 22 Health, are regulated. Therefore, professionals in this field should possess integrated knowledge and skills, be able to solve complex tasks and problems in the field of pharmacy and healthcare, both in practice and during the learning process. This involves conducting research, implementing innovations, and is characterized by uncertain conditions and requirements. A modern approach also involves the use of highly efficient technologies in the national and international educational and scientific environments, which ensure the preparation of competitive, highly qualified pharmaceutical professionals with moral and spiritual values, social responsibility, and community orientation. They are capable of providing quality pharmaceutical care to people and possess «soft skills».&#x0D; Upon the development of the approved higher education standard for the specialty of 226 Pharmacy, Industrial Pharmacy by the Ministry of Education and Science of Ukraine, the educational and professional programs Pharmacy and Perfume and Cosmetic Technologies were revised, and a list of competences as well as program learning outcomes for future pharmaceutical professionals was specified. These were aligned with the demands of the labor market and a professional-oriented approach, based on the concept of competences for a modern pharmacist and the variable components of educational and professional training programs

Experimental demonstration of a skyrmion-enhanced strain-mediated physical reservoir computing system

Physical reservoirs holding intrinsic nonlinearity, high dimensionality, and memory effects have attracted considerable interest regarding solving complex tasks efficiently. Particularly, spintronic and strain-mediated electronic physical reservoirs are appealing due to their high speed, multi-parameter fusion and low power consumption. Here, we experimentally realize a skyrmion-enhanced strain-mediated physical reservoir in a multiferroic heterostructure of Pt/Co/Gd multilayers on (001)-oriented 0.7PbMg1/3Nb2/3O3−0.3PbTiO3 (PMN-PT). The enhancement is coming from the fusion of magnetic skyrmions and electro resistivity tuned by strain simultaneously. The functionality of the strain-mediated RC system is successfully achieved via a sequential waveform classification task with the recognition rate of 99.3% for the last waveform, and a Mackey-Glass time series prediction task with normalized root mean square error (NRMSE) of 0.2 for a 20-step prediction. Our work lays the foundations for low-power neuromorphic computing systems with magneto-electro-ferroelastic tunability, representing a further step towards developing future strain-mediated spintronic applications.

Improvement accuracy in deep learning: An increasing neurons distance approach with the penalty term of loss function

The increasing use of neural networks for solving complex tasks has emphasized the need to optimize their performance. In recent years, the development of neural networks has enabled them to tackle increasingly challenging problems for applications in various fields. Existing methods, such as L1 and L2 penalty terms, improve the neural network performance by reducing the neurons' weight and removing some neurons' output. However, these algorithms reduce the number of active neurons and the theoretical maximum capacity of the neural network. A loss function penalty term can improve the network performance by guiding the gradient descent direction of neurons during the training process. Moreover, it does not need to alter the network structure, increase the data, or change the training process. In this study, a novel algorithm is proposed to improve the performance of the network by adding a new loss function penalty term. The algorithm proposed in this study enhances the accuracy and anti-interference capabilities of neural networks by increasing the number of active neurons based on the finding that identical neurons extract identical features from the data, while distinct neurons extract unique features. The neurons are treated as hyperspace points and the distance between them is converted into repulsive forces to increase the distance between these points. To verify the validity of the proposed algorithm, we tested it on image classification datasets (CIFAR-100 and CALTECH-256), text datasets (SST-2 and THUCNews), and an image detection dataset (PASCAL VOC). The results show that the proposed algorithm can improve the network performance for a variety of neural network structures, data types, and task types. This algorithm has demonstrated its effectiveness in robustness against data noise and compatibility with pre-trained models such as Faster R-CNN, YOLO, and RetinaNet.

COMMUNICATION APPROACHES TO THE PROMOTION OF THE REGIONAL STRATEGY AND ENSURING THE COMPETITIVENESS OF THE REGION

The article examines the tools, measures and means used in the field of modern promotion of regional strategy in order to solve complex tasks and practical problems of ensuring their competitiveness at the national and international levels. The authors suggested systematizing the communication toolkit according to groups (measures, means, tools), and in each of the groups to distinguish specific features (measures should be divided by the sphere of activity, by types, by the direction of influence, by goals; tools – by communication and technological features; means - according to technical possibilities of communication, television, radio, Internet). This makes it possible to deepen the understanding of each of the elements of the toolkit and to formulate recommendations for their more effective use in the promotion of regions. The authors proposed to improve the theoretical and methodological approach to the formation of instrumental means, taking into account the goals and mutual coordination of the elements of the management system.

DIRECTIONS OF APPLICATION OF ARTIFICIAL INTELLIGENCE IN GEODESIC MONITORING OF BUILDINGS AND STRUCTURES

The study determined the necessity of using artificial intelligence in solving the tasks of geodetic monitoring of buildings and structures. According to the results of the research, examples of the world experience of involving artificial intelligence in solving various issues of geodetic monitoring were found. The issues of using modern instrument equipment in conducting geodetic monitoring with the use of artificial intelligence are investigated. Therefore, the application of artificial intelligence in geodetic monitoring of buildings and structures can significantly increase the efficiency and accuracy of data collection and analysis, reduce risks and increase the safety of workers and the public, as well as reduce costs and increase the productivity of processes. There are various examples of the application of artificial intelligence in geodetic monitoring of buildings and structures, such as the use of machine learning to predict landslides, the use of autonomous drones to collect data, and automatic image processing systems to detect defects and damage to buildings. The use of artificial intelligence in geodetic monitoring of buildings and structures has great potential for improving the safety, efficiency and productivity of construction processes. In addition, the development of artificial intelligence and its application in geodesy can help solve complex tasks, such as predicting floods, earthquakes and other dangerous phenomena related to geodesy and construction. The application of artificial intelligence can also increase the accuracy and reliability of surveying and mapping, which can be useful for solving many different problems related to surveying and construction. In this regard, it can be argued that artificial intelligence has already found its application in geodesy and construction, and its capabilities are still being explored and developed. This opens up many opportunities to improve the efficiency and accuracy of construction processes, reduce risks and increase the safety of workers and the public, as well as to create new innovations and achievements in the field of surveying and construction. Keywords: artificial intelligence, geodetic monitoring, geoinformation system, automation, camera works, monitoring principles, building and construction monitoring data, geospatial analysis, construction objects.

Distributional and hierarchical reinforcement learning for physical systems with noisy state observations and exogenous perturbations

Reinforcement learning has shown remarkable success in various applications, and in some cases, even outperforms human performance. However, despite the potential of reinforcement learning, numerous challenges still exist. In this paper, we introduce a novel approach that exploits the synergies between hierarchical reinforcement learning and distributional reinforcement learning to address complex sparse-reward tasks, where noisy state observations or non-stationary exogenous perturbations are present. Our proposed method has a hierarchical policy structure, where random rewards are modeled as random variables that follow a value distribution. This approach enables the handling of complex tasks and increases robustness to uncertainties arising from measurement noise or exogenous perturbations, such as wind. To achieve this, we extend the distributional soft Bellman operator and temporal difference error to include the hierarchical structure, and we use quantile regression to approximate the reward distribution. We evaluate our method using a bipedal robot in the OpenAI Gym environment and an electric autonomous vehicle in the SUMO traffic simulator. The results demonstrate the effectiveness of our approach in solving complex tasks with the aforementioned uncertainties when compared to state-of-the-art methods. Our approach demonstrates promising results in handling uncertainties caused by noise and perturbations for challenging sparse-reward tasks, and could potentially pave the way for the development of more robust and effective reinforcement learning algorithms in real physical systems.

Scaling Up Q-Learning via Exploiting State–Action Equivalence

Recent success stories in reinforcement learning have demonstrated that leveraging structural properties of the underlying environment is key in devising viable methods capable of solving complex tasks. We study off-policy learning in discounted reinforcement learning, where some equivalence relation in the environment exists. We introduce a new model-free algorithm, called QL-ES (Q-learning with equivalence structure), which is a variant of (asynchronous) Q-learning tailored to exploit the equivalence structure in the MDP. We report a non-asymptotic PAC-type sample complexity bound for QL-ES, thereby establishing its sample efficiency. This bound also allows us to quantify the superiority of QL-ES over Q-learning analytically, which shows that the theoretical gain in some domains can be massive. We report extensive numerical experiments demonstrating that QL-ES converges significantly faster than (structure-oblivious) Q-learning empirically. They imply that the empirical performance gain obtained by exploiting the equivalence structure could be massive, even in simple domains. To the best of our knowledge, QL-ES is the first provably efficient model-free algorithm to exploit the equivalence structure in finite MDPs.

An Efficient Optimization Technique for Training Deep Neural Networks

Deep learning is a sub-branch of artificial intelligence that acquires knowledge by training a neural network. It has many applications in the field of banking, automobile industry, agriculture, and healthcare industry. Deep learning has played a significant role in solving complex tasks related to computer vision, such as image classification, natural language processing, and object detection. On the other hand, optimizers also play an intrinsic role in training the deep learning model. Recent studies have proposed many deep learning models, such as VGG, ResNet, DenseNet, and ImageNet. In addition, there are many optimizers such as stochastic gradient descent (SGD), Adam, AdaDelta, Adabelief, and AdaMax. In this study, we have selected those models that require lower hardware requirements and shorter training times, which facilitates the overall training process. We have modified the Adam based optimizers and minimized the cyclic path. We have removed an additional hyper-parameter from RMSProp and observed that the optimizer works with various models. The learning rate is set to minimum and constant. The initial weights are updated after each epoch, which helps to improve the accuracy of the model. We also changed the position of the epsilon in the default Adam optimizer. By changing the position of the epsilon, it accumulates the updating process. We used various models with SGD, Adam, RMSProp, and the proposed optimization technique. The results indicate that the proposed method is effective in achieving the accuracy and works well with the state-of-the-art architectures.