Search results

Many practical control problems require achieving multiple objectives, and these objectives often conflict with each other. The existing multi-objective evolutionary reinforcement learning algorithms cannot achieve good search results when solving such problems. It is necessary to design a new multi-objective evolutionary reinforcement learning algorithm with a stronger searchability.

The multi-objective reinforcement learning algorithm proposed in this paper is based on the evolutionary computation framework. In each generation, this study uses the long-short-term selection method to select parent policies. The long-term selection is based on the improvement of policy along the predefined optimization direction in the previous generation. The short-term selection uses a prediction model to predict the optimization direction that may have the greatest improvement on overall population performance. In the evolutionary stage, the penalty-based nonlinear scalarization method is used to scalarize the multi-dimensional advantage functions, and the nonlinear multi-objective policy gradient is designed to optimize the parent policies along the predefined directions.

The penalty-based nonlinear scalarization method can force policies to improve along the predefined optimization directions. The long-short-term optimization method can alleviate the exploration-exploitation problem, enabling the algorithm to explore unknown regions while ensuring that potential policies are fully optimized. The combination of these designs can effectively improve the performance of the final population.

A multi-objective evolutionary reinforcement learning algorithm with stronger searchability has been proposed. This algorithm can find a Pareto policy set with better convergence, diversity and density.

The call for a new paradigm in politics and governance has become a planetary imperative. Humanity is at a critical juncture; unless we mature as a species and become net-positive to nature the human experiment may (soon) end. We have become our own biggest threat. This chapter explores the foundations, as well as systemic barriers, for the shift to a new and life-centred paradigm in politics and governance. Offering a systemic exploration of the root causes of our sustainability crises and how to address this, based on the cosmology and evolutionary principles of complex living systems. Applying Living Systems Protocols from the EARTHwise Constitution for a Planetary Civilization, and its framework of five Future Archetypes, for developing our transformative capacities to address the systemic thrivability barriers of mechanistic systems and worldviews. With case-study examples of new paradigm tools, systems and technologies that enable a decentralization of governance and democratization of ownership. As such empowering the systemic conditions and maturation pathways for a thriving planetary civilization. The chapter completes with a brief practice for developing our future human capacities and inner consciousness shifts for a new paradigm in politics and governance.

Influencer marketing mediated by social media is prevalent in social commerce. Micro-, meso- and macro-influencers all play an irreplaceable role in marketing. The purpose of this paper is to explore how companies with limited budgets choose influencers according to products' various levels of brand familiarity.

This study constructs an evolutionary game model of influencer marketing based on evolutionary game theory on complex networks. This model initiates various networks to demonstrate how influencers disseminate information and constructs update mechanisms to depict how individuals react to this information based on individuals' information utility and friends' strategies.

Simulation results suggest that companies should invest more in macro-influencers than in meso-influencers, however investing all in macro-influencers is not a good choice. The investment in meso-influencers will increase as brand familiarity decreases, whereas it will not exceed investment in macro-influencers. Furthermore, the accumulation of micro-influencers can accelerate the marketing process.

This study examines the combined effects of micro-influencers, meso-influencers and macro-influencers in marketing by simulating the marketing process initiated by influencers on social media.

This study aims to solve the problem of job scheduling and multi automated guided vehicle (AGV) cooperation in intelligent manufacturing workshops.

In this study, an algorithm for job scheduling and cooperative work of multiple AGVs is designed. In the first part, with the goal of minimizing the total processing time and the total power consumption, the niche multi-objective evolutionary algorithm is used to determine the processing task arrangement on different machines. In the second part, AGV is called to transport workpieces, and an improved ant colony algorithm is used to generate the initial path of AGV. In the third part, to avoid path conflicts between running AGVs, the authors propose a simple priority-based waiting strategy to avoid collisions.

The experiment shows that the solution can effectively deal with job scheduling and multiple AGV operation problems in the workshop.

In this paper, a collaborative work algorithm is proposed, which combines the job scheduling and AGV running problem to make the research results adapt to the real job environment in the workshop.

How does the interaction between time and knowledge affect the evolution of organizations? Past research in organizational evolution has mostly investigated time and knowledge as two separate variables. In contrast, theoretical perspectives integrating these variables are still seemingly scant. The authors believe that filling this literature gap needs attention. Thus, this study aims to contribute by developing a conceptual framework.

This is a conceptual study. The framework is centred on the concept of “co-evolutionary time”, which the authors explain through a business example from the tourism industry. Supported by a narrative-based style, from a methodological point of view the framework is featured by the attempt to synthesize specific, extant literature into new theoretical development.

As its main theoretical contribution, the co-evolutionary time suggests how firms can adapt in a way that, from an evolutionary perspective, proves fitting both in terms of contents and methods, thus opening possibilities for new long-term social construction and reconstruction. As its main practical contribution, co-evolutionary time can constitute not only a temporary source of organizational success and competitive advantage but also an agent of enduring change and long-term business survival.

As its main novelty, the framework is developed through merging two literature streams. In particular, the authors first consider the literature about time, with a focus on its objective and subjective dimensions. The authors then consider the literature about organizational evolution, with a focus on the co-evolutionary nature of the firm/environment relationship.

Healthcare education is a huge industry with a significant social footprint and resilient impact on well-being and on the quality of life. It integrates diverse scientific domains and needs to continuously update its value proposition to reflect the need for preparing top-quality health professionals. It also has to support professional development and to manage effectively the accreditation of programs and the certification of skills and knowledge. In this chapter, the authors expand a theoretical framework about Active and Transformative Learning (ATL) that has introduced in the volume of ATL for STEAM disciplines and also discussed how artificial intelligent (AI) tools, such as OPENAI Chat GPT, can serve as transformers and value carriers for the implementation of ATL activities and use cases in healthcare education.

This paper aims to introduce the concept of Entrepreneurial Collective Intelligence (ECI) as a means of understanding how communities of entrepreneurial actors learn to act both collectively and knowingly. It explores how connections between processes of CI, agency and action can explain and enable the development entrepreneurial community organisations.

There is a selective literature review of prior works on the related fields of community and collective entrepreneurship; collectives and intelligence; agency and action. The review is used to propose a framework of collective entrepreneurial intelligence, agency and action. An interpretive approach is used to research four case studies of community organisations which use CI to generate entrepreneurial outcomes.

The cases are compared with themes from prior literature to develop a conceptual model of four ECI processes which enable intelligence, agency and action: collaborative processes; distributed working; intelligence representations and organisation of infrastructures. These are theorised to discuss ideas, challenges, methods and questions to enhance entrepreneurial actions, based on sharing knowledge and learning, in the context of collective agency, action and intelligence.

The four processes, both together and separately, represent a coherent framework useful for further studies on the role of collectives in enterprising communities.

The four processes each represent a central area of attention, not only for development, learning, decision-making and leadership within enterprising communities but also for entrepreneurship education in terms of alternative didactics, pedagogies and learning forms.

The improved knowledge on the role of collective agency and CI within entrepreneurial processes is useful for strengthening civil activism and other fruitful forms of entrepreneurial collective processes. This may help solve complicated societal problems where traditional conceptions of entrepreneurship fail.

The conceptual contribution is to explain the dynamic relationships between ECI and action, mediated by collective agency. The role of CI in informing entrepreneurial communities is explored and four enabling processes are proposed. This coherent framework is useful for further studies on the role of collectives in enterprising communities, whilst informing their learning, decision-making and leadership.

This research aims to explore leadership approaches that foster deeper learning and facilitate the transition from traditional schooling to a model aligned with the demands of the post-industrial digital knowledge society.

Employing a mixed-methods approach, the authors conducted surveys among school principals within a network of schools embracing deeper learning based on ten distinct but interlocking criteria that define this particular model of deeper learning. Through in-depth follow-up interviews with school leaders, the authors investigated the factors and obstacles that support sustainable implementation and scalability of deeper learning, with a specific focus on the role of transformational leadership.

During the implementation of transformative practices like deeper learning, school leaders demonstrate diverse perspectives on the necessary changes for their successful integration. Leaders inclined toward a “transactional” leadership style concentrate on changes within individual classrooms. Conversely, leaders exemplifying “transformational leadership” possess a broader vision and address systemic factors such as teacher collaboration, assessment regulations and the effective utilization of time and space within schools. To achieve widespread adoption of deeper learning across schools and the education system, it is essential to recruit more transformational leaders for formal leadership positions and reorient leadership training toward transformational approaches.

The deeper learning model developed for this intervention encompasses a four-stage process: Teachers initially collaborate in small teams to co-design interdisciplinary, deeper learning units. The actual units consist of three sequences: knowledge acquisition, where students gain knowledge through direct instruction supplemented by personalized learning on digital platforms; team-based co-creative and co-constructive tasks facilitated by teachers once students have acquired a solid knowledge base and the completion of authentic tasks, products or performances in sequence III. While small groups of intrinsically motivated teachers have successfully implemented the model, achieving broader scalability and dissemination across schools requires significant “transformational leadership” to challenge traditional norms regarding teacher collaboration, assessment practices and the efficient use of time and space in schools.

This paper presents a structured model of deeper learning based on ten distinct but interlocking quality criteria tested within a network of 26 schools. The model has demonstrated transformative effects on participating schools, albeit primarily observed in smaller substructures of large secondary schools. Teachers who previously worked independently have begun to collaboratively design learning experiences, resulting in “hybrid” classrooms where physical and digital spaces merge and extend to include maker spaces and out-of-school learning environments. Traditional summative assessments have been replaced by various forms of embedded formative assessment. However, these innovations are currently driven by small groups of intrinsically motivated teachers. The research provides insights into the type of school leadership necessary for comprehensive scaling and system-wide dissemination of deeper learning.

Student interest and learning success is an important component of teaching learning research. However, while the impact of emotions and psychological needs on students' achievements has been a focus of research, the impact of their physiological needs has been under studied. In this explorative study, I examine what impact the physiological and psychological needs of student teachers have on their feelings, motivation, and interest in different learning settings.

The research method used was the daily reconstruction method and included the Felix-App, a new digital research and feedback tool that allows the measurement of feelings, needs, motivation, and interest in real time.

The results suggest the importance of physiological needs for perceived emotions, motivation, and interest in the learning subject. The psychological needs, on the other hand, are of less importance.

The Felix-App is an innovative tool to learn more about learners' emotions and needs in real learning settings. The importance of physiological needs has been known since Maslow, but should be considered much more in the context of teaching and learning research in the future. There is a need for further research on the importance of physical aspects in learning.

The promotion of autonomous vehicles introduces privacy and security risks, underscoring the pressing need for responsible innovation implementation. To more effectively address the societal risks posed by autonomous vehicles, considering collaborative engagement of key stakeholders is essential. This study aims to provide insights into the governance of potential privacy and security issues in the innovation of autonomous driving technology by analyzing the micro-level decision-making processes of various stakeholders.

For this study, the authors use a nuanced approach, integrating key stakeholder theory, perceived value theory and prospect theory. The study constructs a model based on evolutionary game for the privacy and security governance mechanism of autonomous vehicles, involving enterprises, governments and consumers.

The governance of privacy and security in autonomous driving technology is influenced by key stakeholders’ decision-making behaviors and pivotal factors such as perceived value factors. The study finds that the governmental is influenced to a lesser extent by the decisions of other stakeholders, and factors such as risk preference coefficient, which contribute to perceived value, have a more significant influence than appearance factors like participation costs.

This study lacks an investigation into the risk sensitivity of various stakeholders in different scenarios.

The study delineates the roles and behaviors of key stakeholders and contributes valuable insights toward addressing pertinent risk concerns within the governance of autonomous vehicles. Through the study, the practical application of Responsible Innovation theory has been enriched, addressing the shortcomings in the analysis of micro-level processes within the framework of evolutionary game.