Exploring selfish reinforcement learning in repeated games with stochastic rewards

In this paper we introduce a new multi-agent reinforcement learning algorithm, called exploring selfish reinforcement learning (ESRL). ESRL allows agents to reach optimal solutions in repeated non-zero sum games with stochastic rewards, by using coordinated exploration. First, two ESRL algorithms for respectively common interest and conflicting interest games are presented. Both ESRL algorithms are based on the same idea, i.e. an agent explores by temporarily excluding some of the local actions from its private action space, to give the team of agents the opportunity to look for better solutions in a reduced joint action space. In a latter stage these two algorithms are transformed into one generic algorithm which does not assume that the type of the game is known in advance. ESRL is able to find the Pareto optimal solution in common interest games without communication. In conflicting interest games ESRL only needs limited communication to learn a fair periodical policy, resulting in a good overall policy. Important to know is that ESRL agents are independent in the sense that they only use their own action choices and rewards to base their decisions on, that ESRL agents are flexible in learning different solution concepts and they can handle both stochastic, possible delayed rewards and asynchronous action selection. A real-life experiment, i.e. adaptive load-balancing of parallel applications is added.     

Product information visualization and augmentation in collaborative design

In this paper, a collaborative system for product information visualization and augmentation is presented. The developed system allows the users, who can be remotely distributed, to view a product model, which is a geometric representation of the product, from different perspectives. They can choose to view design and product history, such as previous modification processes and feature information of the product independently. The product models displayed to the users are immediately updated after any design modifications have been made to the CAD model. Product features being discussed can be highlighted to draw the users’ attention. In addition, modifications can be displayed dynamically for the users to evaluate the design effect. The product history document module in the system provides a user-friendly interface for retrieving design records. After a specific record has been chosen, the related product model is displayed, and it can be aligned with the current product model for the ease of comparison and evaluation. The feature information of the product is displayed using virtual “floating” annotations linked to the related features. A user interface to enter annotations is provided, and the annotations entered by different users can be shared in real time. A cluster-based greedy algorithm is implemented to avoid overlapping annotations in the field of view.     

A framework for the design and integration of collaborative classroom games

The progress registered in the use of video games as educational tools has not yet been successfully transferred to the classroom. In an attempt to close this gap, a framework was developed that assists in the design and classroom integration of educational games. The framework addresses both the educational dimension and the ludic dimension. The educational dimension employs Bloom’s revised taxonomy to define learning objectives and applies the classroom multiplayer presential game (CMPG) pedagogical model while the ludic dimension determines the gaming elements subject to constraints imposed by the educational dimension. With a view to validating the framework, a game for teaching electrostatics was designed and experimentally implemented in a classroom context. An evaluation based on pre/post testing found that the game increased the average number of correct answers by students participating in the experiment from 6.11 to 10.00, a result found to be statistically significant. Thus validated, the framework offers a promising basis for further exploration through the development of other games and fine-tuning of its components.     

Exploring young students' talk in iPad-supported collaborative learning environments

In the few years since its release, Apple's iPad has generated much discussion about its potential to support student learning at all levels of the education system. Much of this has focused on its physical and technical attributes, such as portability, touch-display, connectivity, and large array of apps. However, a few studies have begun to explore possible advantages of iPads being used as public work spaces, enabling students to interact more collaboratively when creating learning outputs. These studies point to other affordances such as the iPad's ability to lay flat on a desk or be propped at a convenient angle, its wide viewing range and multi-user accessible interface, as being particularly relevant in supporting collaboration.Between June and November 2013, researchers from the University of Waikato used a specifically developed ‘observeware’ app to capture display and audio data while young students (5 year olds) were using iPads in pairs for developing numeracy, literacy and problem-solving/decision-making skills. The study used Mercer's (1994) talk types framework to explore the nature of talk students engaged in while they were using the iPads and interacting with each other and their teacher, and also how features of the device may have influenced this.Results indicated exceptionally high levels of on-task talk, but that this was mostly of an affirming and non-critical nature and unsupportive of outcome improvement or refinement. While the iPad offered unique potential as a shared, public learning device, the pedagogical role of the teacher in realising this by helping students learn appropriate ‘ground rules’ to raise talk quality, was critical. This article details the methodology used and the results of the study. It discusses the important role teachers play in helping young students build oral-interaction strategies to capitalise on high levels of learning engagement, and the unique features of these devices.     

Understanding mobile technology-fit behaviors outside the classroom

An increase in mobile device usage among college students has been documented in different countries. We provide a solid theoretical and empirical foundation for mobile learning in the context of distance education, and more guidance in terms of how to utilize emerging mobile technologies and to integrate them into their teaching more effectively. This research focuses on a deeper understanding of how learners use mobiles as learning tools outside the classroom. Our results are based on a specific population drawn from two different countries, in which the US (United States) population reflected students from the education field, while the students from Israel are drawn more from the engineering and science fields. The findings of this study contribute to the generalizations to the education field and information system designers who need to analyze and design mobile-learning (m-learning) applications to be used outside the classroom.     

Exploring augmented reality for worker assistance versus training

This paper aims at advancing the fundamental understanding of the affordances of Augmented Reality (AR) as a workplace-based learning and training technology in supporting manual or semi-automated manufacturing tasks that involve both complex manipulation and reasoning. Between-subject laboratory experiments involving 20 participants are conducted on a real-life electro-mechanical assembly task to investigate the impacts of various modes of information delivery through AR compared to traditional training methods on task efficiency, number of errors, learning, independence, and cognitive load. The AR application is developed in Unity and deployed on HoloLens 2 headsets. Interviews with experts from industry and academia are also conducted to create new insights into the affordances of AR as a training versus assistive tool for manufacturing workers, as well as the need for intelligent mechanisms that enable adaptive and personalized interactions between workers and AR. The findings indicate that despite comparable performance between the AR and control groups in terms of task completion time, learning curve, and independence from instructions, AR dramatically decreases the number of errors compared to traditional instruction, which is sustained after the AR support is removed. Several insights drawn from the experiments and expert interviews are discussed to inform the design of future AR technologies for both training and assisting incumbent and future manufacturing workers on complex manipulation and reasoning tasks.     

The learning kit project: Software tools for supporting and researching regulation of collaborative learning

Computer-supported collaborative learning (CSCL) is a dynamic and varied area of research. Ideally, tools for CSCL support and encourage solo and group learning processes and products. However, most CSCL research does not focus on supporting and sustaining the co-construction of knowledge. We identify four reasons for this situation and identify three critical resources every collaborator brings to collaborations that are underutilized in CSCL research: (a) prior knowledge, (b) information not yet transformed into knowledge that is judged relevant to the task(s) addressed in collaboration, and (c) cognitive processes used to construct these informational resources. Finally, we introduce gStudy, a software tool designed to advance research in the learning sciences. gStudy helps learners manage cognitive load so they can re-assign cognitive resources to self-, co-, and shared regulation; and it automatically and unobtrusively traces each user′s engagement with content and the means chosen for cognitively processing content, thus generating real-time performance data about processes of collaborative learning.     

Exploring students' flow experiences in business simulation games

Business simulation games are a motivational and engaging tool for teaching business management. However, relatively little is known about what factors contribute to their success. This study explores the role of flow experienced while using business simulation games. Specifically, this research investigates the influence of challenge, skills, feedback, and goal clarity on students' flow experience. It also explores the impact of flow on generic skills development, perceived learning, and satisfaction. Based on a survey of 167 undergraduate students who used a classroom‐based business simulation game, the findings show that the challenge provided by the game, students' skills to meet the challenge, and instant feedback positively influenced students' flow. Conversely, goal clarity did not foster the optimal experience. Flow positively impacted generic skills development, perceived learning, and satisfaction.     

Multiplayer online games as educational tools: Facing new challenges in learning

This paper outlines a proposal for the development of educational multiplayer online games based on the activity theory, as an alternative to the current trend in multiplayer gaming and a means of promoting collaboration among students. In order to examine whether online games are engaging for learners, we consider multiple factors regarding game play – such as frequency of game use, gender differences, identification with the characters, and game preferences – as well as some psychosocial factors that may influence learning – such as academic performance, self-esteem, and computer self-efficacy. This paper suggests that online multiplayer educational games should be approached as a complex learning system, based on the principles of activity theory, where the Subjects would interact with other Subjects, Objects and Tools of the game, under specified Rules and create Communities through division of labor, leading to the expected learning outcome. Thus, we suggest taking into account some important issues concerning the Subjects that the activity theory refers to, such as gender differences in playing games, academic performance, self-esteem and computer self-efficacy.     

On the usability and likeability of virtual reality games for education: The case of VR-ENGAGE

Educational software games aim at increasing the students’ motivation and engagement while they learn. However, if software games are targeted to school classrooms they have to be usable and likeable by all students. Usability of virtual reality games may be a problem because these games tend to have complex user interfaces so that they are more attractive. Moreover, if the games acquire an educational content they may lose the attractiveness and appeal that they have on users who are familiar with commercial games. Consequently, likeability may also be questioned. In this paper, we address the issue of usability and likeability of a virtual reality game that is meant to teach students geography. We describe the evaluation experiments conducted, which involved three categories of students in terms of their level of game-playing expertise: novice, intermediate and expert game players. The evaluation results showed that the game was indeed usable and likeable but there was scope for usability and likeability improvement so that the educational benefits may be maximised for all categories of students. The evaluation studies reported in this paper, revealed important issues about further research on virtual reality educational games.     

Exploring the antecedents of team performance in collaborative learning of computer software

As teamwork becomes common in computer software learning, there is an increasing need to study factors contributing to team performance. To this pursuit, the concept of collective efficacy offers great potential to researchers of information systems (IS). Drawing upon social cognitive theory (SCT), this study examines the relationships among computer collective efficacy (CCE), outcome expectations and team performance in the context of collaborative learning. Computer collective efficacy is further divided into two constructs, general CCE and specific CCE. Their causal relationships with two other constructs, performance and outcome expectations, are then investigated using longitudinal data collected from 188 groups of students of an 18-week computer software course. The results indicate that a team’s software learning performance is strongly influenced by specific CCE and outcome expectations, which in turn are influenced by prior performance and general CCE. Finally, prior performance of a group has no direct impact on its subsequent performance.     

A web based collaborative testing environment

This paper presents a computer supported collaborative testing system built upon the Siette web-based assessment environment. The application poses the same set of questions to a group of students. Each student in the group should answer the same question twice. An initial response is given individually, without knowing the answers of others. Then the system provides some tools to show the other partners' responses, to support distance collaboration. Finally a second individual answer is requested. In this way assessment and collaboration activities are interlaced. At the end of a collaborative testing session, each student will have two scores: the initial score and the final score. Three sets of experiments have been carried out: (1) a set of experiments designed to evaluate and fine tune the application, improve usability, and to collect users' feelings and opinions about the system; (2) a second set of experiments to analyze the impact of collaboration in test results, comparing individual and group performance, and analyzing the factors that correlate to those results; and (3) a set of experiments designed to measure individual short-term learning directly related to the collaborative testing activity. We study whether the use of the system is associated with actual learning, and whether this learning is directly related to collaboration between students. Our studies confirm previous results and provide the following evidence (1) the performance increase is directly related to the access to other partners' answers; (2) a student tends to reach a common answer in most cases; and (3) the consensus is highly correlated with the correct response. Moreover, we have found evidence indicating that most of the students really do learn from collaborative testing. High-performing students improve by self-reflection, regardless the composition of the group, but low-performing students need to be in a group with higher-performing students in order to improve.     

Applying adaptive swarm intelligence technology with structuration in web-based collaborative learning

One of the key challenges in the promotion of web-based learning is the development of effective collaborative learning environments. We posit that the structuration process strongly influences the effectiveness of technology used in web-based collaborative learning activities. In this paper, we propose an ant swarm collaborative learning (ASCL) environment based on a swarm intelligence system (SIS) that structures opportunities for effective collaboration and learning in a dynamic way. The results of our experiments indicate that: (1) the self-organizing behavior of SIS is positively associated with system appropriation; (2) the multi-agent-based mechanism of SIS is positively associated with system appropriation; (3) the cohesive capability of SIS is positively associated with system appropriation; and (4) the learner’s tendency toward system appropriation is positively associated with learning effectiveness. Our findings also show that learners in an ASCL environment outperform their counterparts in a general web-based learning (GWL) environment. We conclude that different types of technological support can influence the achievement in a web-based learning environment.     

A recommender agent based on learning styles for better virtual collaborative learning experiences

Almost unlimited access to educational information plethora came with a drawback: finding meaningful material is not a straightforward task anymore. Based on a survey related to how students find additional bibliographical resources for university courses, we concluded there is a strong need for recommended learning materials, for specialized online search and for personalized learning tools. As a result, we developed an educational collaborative filtering recommender agent, with an integrated learning style finder. The agent produces two types of recommendations: suggestions and shortcuts for learning materials and learning tools, helping the learner to better navigate through educational resources. Shortcuts are created taking into account only the user’s profile, while suggestions are created using the choices made by the learners with similar learning styles. The learning style finder assigns to each user a profile model, taking into account an index of learning styles, as well as patterns discovered in the virtual behavior of the user. The current study presents the agent itself, as well as its integration to a virtual collaborative learning environment and its success and limitations, based on users’ feedback.     

The pedagogical challenges to collaborative technologies

Collaborative technologies offer a range of new ways of supporting learning by enabling learners to share and exchange both ideas and their own digital products. This paper considers how best to exploit these opportunities from the perspective of learners’ needs. New technologies invariably excite a creative explosion of new ideas for ways of doing teaching and learning, although the technologies themselves are rarely designed with teaching and learning in mind. To get the best from them for education we need to start with the requirements of education, in terms of both learners’ and teachers’ needs. The argument put forward in this paper is to use what we know about what it takes to learn, and build this into a pedagogical framework with which to challenge digital technologies to deliver a genuinely enhanced learning experience.     

An augmented reality approach for supporting panel alignment in car body assembly

One of the major problems in automotive assembly consists in achieving alignment within the specified tolerances between car panels that make up the exterior bodywork. To reduce errors and time requested to perform the assigned assembly tasks, workers should be guided during these panel fitting operations. Augmented Reality (AR) could be particularly suitable in this regard, as it represents one of the most promising tools to support personnel, with constantly growing applications in production processes. Following this trend, the present work aims to present an AR prototype system for supporting the operator during panel fitting operations of car body assembly, by providing instructions to correct alignment errors in terms of gap and flushness. A real case study concerning the fine alignment of car body panels with respect to the front light projector is also presented.     

Bridging the gap between students and computers: supporting activity awareness for network collaborative learning with GSM network

The internet has been widely used to promote collaborative learning among students. However, students do not always have access to the system, leading to doubt in the interaction among the students, and reducing the effectiveness of collaborative learning, since the web-based collaborative learning environment relies entirely on the availability of computers and the internet. A web-based collaborative learning scheme based on activity awareness carried out through mobile phones is proposed herein. The proposed mechanism automatically sends SMS messages on a GSM network, based on student identity and learning activity, making the student aware of the collaborative learning context, and further improving the student's learning. A web-based collaborative learning activity was implemented in a Taiwan undergraduate class to examine the proposed scheme. Experiments demonstrated that awareness of the collaborative learning context through mobile phones significantly increased student participation in learning activity and improving student learning performance.     

The role of collective efficacy, cognitive quality, and task cohesion in computer-supported collaborative learning (CSCL)

Research has suggested that CSCL environments contain fewer social context clues, resulting in various group processes, performance or motivation. This study thus attempts to explore the relationship among collective efficacy, group processes (i.e. task cohesion, cognitive quality) and collaborative performance in a CSCL environment. A total of 75 Taiwanese college students (divided into 25 groups) participated in the study. Both quantitative and qualitative methods were applied for data analysis. The results indicate that collective efficacy significantly predicted task cohesion but not cognitive quality in the CSCL environment. For the role of group processes in performance, both task cohesion and cognitive quality significantly predicted group performance, but cognitive quality predicted better than task cohesion. In addition, for the predictive capability of prior performance, task cohesion, and cognitive quality in collective efficacy, the results showed that only task cohesion predicted subsequent collective efficacy significantly in the CSCL environment.