Search results

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

This study attempts to answer the question: “how are the two drivers, accountability focus and organizational learning, independently and interactively associated with public agencies’ proactive policy orientation?” The first driver is the multiple accountabilities that public agencies pursue: (1) bureaucratic, (2) legal, (3) professional and (4) political. The second driver is the organizational learning activities of public agencies: (1) socialization, (2) externalization, (3) combination and (4) internalization.

For data, 800 respondents from the public agencies in South Korea were surveyed.

The analysis provided several findings: (1) the discretionary accountabilities (professional and political) have a greater positive influence on the proactive policy orientation; (2) the conventional accountabilities (legal and bureaucratic) tend to have negative impacts on the proactive policy orientation and (3) among the four types of accountability, legal accountability can be more significantly complemented by organizational learning activities, which can enable both visionary and realistic administration in a balanced manner.

This study provides a unique insight on how organizational proactivity can be ensured through the interactions of organizational accountabilities and organizational learning.

This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.

Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.

The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.

The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.

Limited by the types of sensors, the state information available for musculoskeletal robots with highly redundant, nonlinear muscles is often incomplete, which makes the control face a bottleneck problem. The aim of this paper is to design a method to improve the motion performance of musculoskeletal robots in partially observable scenarios, and to leverage the ontology knowledge to enhance the algorithm’s adaptability to musculoskeletal robots that have undergone changes.

A memory and attention-based reinforcement learning method is proposed for musculoskeletal robots with prior knowledge of muscle synergies. First, to deal with partially observed states available to musculoskeletal robots, a memory and attention-based network architecture is proposed for inferring more sufficient and intrinsic states. Second, inspired by muscle synergy hypothesis in neuroscience, prior knowledge of a musculoskeletal robot’s muscle synergies is embedded in network structure and reward shaping.

Based on systematic validation, it is found that the proposed method demonstrates superiority over the traditional twin delayed deep deterministic policy gradients (TD3) algorithm. A musculoskeletal robot with highly redundant, nonlinear muscles is adopted to implement goal-directed tasks. In the case of 21-dimensional states, the learning efficiency and accuracy are significantly improved compared with the traditional TD3 algorithm; in the case of 13-dimensional states without velocities and information from the end effector, the traditional TD3 is unable to complete the reaching tasks, while the proposed method breaks through this bottleneck problem.

In this paper, a novel memory and attention-based reinforcement learning method with prior knowledge of muscle synergies is proposed for musculoskeletal robots to deal with partially observable scenarios. Compared with the existing methods, the proposed method effectively improves the performance. Furthermore, this paper promotes the fusion of neuroscience and robotics.

The purpose of this study is to demonstrate the strategy and innovation of the Faculty of Adab and Humanities in developing the quality of education in digital era by using anthropology of education approach.

In accordance with the research purpose to demonstrate the strategy and innovation of the Faculty of Adab and Humanities in developing the quality of education in the digital era using an educational anthropology approach, the method used is descriptive qualitative, which refers to data in the form of interviews obtained from the field.

The results of this research indicate that there are strategies and innovations to develop the quality of higher education at the Faculty of Adab and Humanities in the digital era. These include adjusting the curriculum with the context of the era, implementing the learning process based on research and reinforcing on aspects of digital literacy among students through the innovation of the library based on digital.

This study can be considered in the process of evaluating policies related to quality reinforcing strategies and innovations at the Faculty of Adab and Humanities in facing the challenges of the times. The study is only limited to tracing and analyzing strategies and innovations to reinforce education in the Faculty of Adab and Humanities and their impact on human resource development. For further research, it can be done in more detail and depth and on a larger scale.

This paper explores optimal service resource management strategy, a continuous challenge for health information service to enhance service performance, optimise service resource utilisation and deliver interactive health information service.

An adaptive optimal service resource management strategy was developed considering a value co-creation model in health information service with a focus on collaborative and interactive with users. The deep reinforcement learning algorithm was embedded in the Internet of Things (IoT)-based health information service system (I-HISS) to allocate service resources by controlling service provision and service adaptation based on user engagement behaviour. The simulation experiments were conducted to evaluate the significance of the proposed algorithm under different user reactions to the health information service.

The results indicate that the proposed service resource management strategy, considering user co-creation in the service delivery, process improved both the service provider’s business revenue and users' individual benefits.

The findings may facilitate the design and implementation of health information services that can achieve a high user service experience with low service operation costs.

This study is amongst the first to propose a service resource management model in I-HISS, considering the value co-creation of the user in the service-dominant logic. The novel artificial intelligence algorithm is developed using the deep reinforcement learning method to learn the adaptive service resource management strategy. The results emphasise user engagement in the health information service process.

The massive expansion of digital platform has been responsible for the widespread progressive engagement created amongst learners and educators. The practice of requiring student feedback on online learning services ensures that teacher education continues to advance its strategic approach to online learning. This paper aims to examine the level of accessibility and adaptability of digital technology with particular focus on Malaysia, by elaborating the value of superior learning service and practical adaptability of online learning during the pandemic era.

This study was conducted using qualitative approach of data collection, namely via structured interview. The listed respondents included 30 higher learners who participated in the study by providing feedback on the issues encountered during the research process.

The findings revealed that the strategic enhancement of digital accessibility continued with digital adaptability to sources of learning services would contribute to advancing achievement of digital learning pathway.

Increasing accessibility to digital platforms in digital learning system can help to shape the digital environment. Digital expansion can create unlimited boundaries for online knowledge acquisition.

The social implication refers to acquiring the abilities developed through online engagement with peers by actualising and exploring information together with continuous inter-connectedness of sharing pathway in online platform. The instructor would need to give a proportional gateway to make learners experience the digital environment for future education.

This study aims to assess the value of developing accessibility of digital technology for students' online learning services during the pandemic and beyond. A well-structured plan would enable digital learning capabilities and mutual accessibility amongst learners. This can allow digital abilities to be transformed into collaborative teamwork amongst learners.

This chapter discusses the extension of legal equality between male and female citizens in four states in North Africa – Tunisia, Egypt, Morocco and Algeria – through one specific lens: A married woman's legal capacity to initiate and obtain divorce without the husband's consent. Building on the works of Stein Rokkan and Reinhard Bendix on the expansion of citizenship to the ‘lower classes’, it is argued that amendments in divorce law by introducing in-court divorce for women, in addition to out-of-court divorce, is a significant institutional change that extends legal equality between men and women. The introduction of in-court divorce expands female citizenship by bolstering woman's juridical autonomy and capacity in state law. Changes in divorce laws are thus part of state centralization by means of standardizing rules that regulate family law through public administrative institutions rather than religious organizations. Two questions are addressed: First, how did amendments in divorce laws occur after independence? Second, in which ways did women's bolstered legal capacity in divorce have a spill over effect on reforms in other patriarchal state laws? Based on observations on sequences of change in four states in North Africa, it is argued that amendments that equalize between men and women in divorce should be seen as a key driver for reforms in other state laws, that reduce legal inequality between male and female citizens. In all four states, women's citizenship was extended in nationality law and criminal law after amendments in divorce law gave women unilateral legal power to exit a marital relationship.

Social enterprises are embedded in ecosystems with multiple actors interested in the field’s growth. One way to enhance social enterprises is through public policies and developing countries like Brazil included this in the public agenda. After an important mobilization of private organizations and public managers, the Brazilian federal government implemented in 2017 the National Impact Investment and Business Strategy (ENIMPACTO) renamed in 2023 to National Impact Economy Strategy with the same abbreviation. Since its creation, ENIMPACTO saw significant modifications leading to a decree in 2023 extending its mandate, amplifying membership and changing its name to the National Impact Economy Strategy while maintaining the same acronym. This experience leads us to the following question: How was ENIMPACTO created and developed?

We used institutional arrangements and advocacy coalition theory to analyze the key elements that contributed to ENIMPACTO’s creation and its evolution through time. A qualitative, single-case study on the Brazilian experience implementing ENIMPACTO was conducted through semi-structured interviews with national strategy members, participant observation, document and data analysis.

We argue that advocacy coalition and institutional arrangements frameworks combined are needed to understand Enimpacto’s complexity. The strategy presented an extensive multiple-actor articulation involving shared beliefs that were also important to gather support on recreating and expanding Enimpacto when external events threatened its continuity. Yet, it presented important challenges on how to achieve consensus and alignment regarding important concepts and regulation strategy among the actors and manage the public policy governance and activities implementation.

We combine institutional arrangements and advocacy coalition frameworks and apply them to analyze a public policy composed of actors of multiple sectors that play an active advocacy coalition role. We also present empirical evidence that elements of the advocacy coalition framework add analytical elements to institutional arrangements literature and how they affect each other. We point to two important elements of the institutional arrangements framework (territoriality and subsidiarity) that were not initially considered by ENIMPACTO and were later incorporated because of tensions in the field. We provide empirical evidence of the incipient role that public administration can play in promoting social enterprises' agenda that might base similar strategies to boost social enterprises in other locations.