Can technologies make a difference for hospitalized youth: Findings from research

Children and youth who are hospitalized for a short or long term become socially isolated from their family, school and classmates. As their isolation increases, so does their vulnerability as a result of disrupted schooling. Research studies suggest different ways of using technologies to overcome this isolation and support children during this critical time of their lives. With technology for children in hospitals becoming increasingly commonplace, evaluating how it is used and its impact on children's learning and well‐being is necessary. In this paper, we systematically evaluated existing research on use of technologies for communication, support and educational purposes and its contribution to the well‐being of hospitalized children. A rigorous selection process yielded 14 research articles meeting the following criteria: empirical studies, using technologies for network of support, targeting hospitalized children and adolescents and targeting learning or social and emotional well‐being in the last decade. This review indicates that the use of technologies with children and youth in hospitals generally increased their potential for learning and improved connectivity with school. Our findings revealed that implementing digital pedagogies and creating online communities were helpful but underutilized features in the research.     

‘I'm a completely different person at home’: using digital technologies to connect learning between home and school

This paper reports on a qualitative study exploring children's, parents', and teachers' experiences of communication between home and school and connections between children's learning at school and home in order to consider how using digital technologies to mediate the home–school relationship might support children's learning. Parents, teachers, and children welcomed the idea of using digital technologies to communicate between home and school, hoping that more timely communication could avoid problems at school. There were few connections between learning at home and in school; participants saw school and home as separate domains and the boundaries between the two were strongly maintained. It is argued that for connections to be made between learning at home and in school, elements of both need to be drawn together in a space in which both are valued, and that digital technologies could support the creation of such virtual third spaces.     

面向动态三维迷宫的综合奖励设计

动态三维迷宫是较为困难的、具有不确定性和不完全信息的强化学习任务环境,使用常规奖励函数在此环境中训练任务,速度缓慢甚至可能无法完成。为解决利用强化学习在动态迷宫中寻找多目标的问题,提出一种基于事件触发的综合奖励方案,该方案将三维迷宫中各种行为状态表达为各种事件,再由事件驱动奖励。奖励分为环境奖励和内部奖励,其中环境奖励与三维迷宫任务直接相关,含有体现任务目标的节点奖励和任务约束的约束奖励。内部奖励与智能体学习过程中的状态感受相关,含有判断奖励和心情奖励。在实验中,综合奖励的性能均值相较于改进奖励提升54.66%,结果表明,综合奖励方案在提高完成任务满意度、增强探索能力、提升训练效率方面具有优势。     

Automated instructional design for CSCL: A hierarchical task network planning approach

In Computer Supported Collaborative Learning (CSCL), one of the most important tasks for instructional designers is to define scenarios that foster group learning. Such scenarios, defined as Units of Learning (UoLs), comprise different components and are organized according to pedagogical approaches to orchestrate group learning processes. Examples of UoL components are learning objects, student roles, student characteristics (e.g., background, preferences, learning styles, etc.), instructional/learning goals, and activities, among others. Thus, the instructional design (ID) of a proper UoL for CSCL is a complex task that requires practice and experience. This is particularly true when designing, developing, adapting, and customizing UoLs, taking into consideration different instructional/learning goals and individual preferences of students. This paper therefore proposes using a Hierarchical Task Network (HTN) planning approach to automate and optimize the tasks of designers. To accomplish that, we define an initial CSCL scenario as “an ID task” and “a set of information related to students and the domain to be taught.” Then we propose a model that formally describes ID for CSCL as HTN planning, where the initial CSCL scenario is adapted and refined according to student needs. In this model, the ID strategies are defined as hierarchical tasks and methods into a planning domain definition, and the initial CSCL scenario is defined as a planning problem definition. To validate our approach, we develop a CSCL courseware generator that (i) helps designers to set up an initial CSCL scenario; (ii) automatically generates a personalized UoL based on a given initial scenario; and (iii) supports the adaptation of UoLs.     

Children's engagement during digital game-based learning of reading: The effects of time,rewards, and challenge

This study investigated the effects of two game features (the level of challenge and the reward system) on first and second graders' engagement during digital game-based learning of reading. We were particularly interested in determining how well these features managed to maintain children's engagement over the 8-week training period. The children (N = 138) used GraphoGame, a web-based game training letter–sound connections, at home under the supervision of parents. Data regarding the children's gaming and engagement were stored on the GraphoGame online server. A 2 × 2 factorial design was used to investigate the effects of the level of challenge (high challenge vs. high success) and the presence of the reward system (present vs. absent). Children's engagement was measured by session frequency and duration and through an in-game self-report survey that was presented at the end of the each session. According to the results, the children enjoyed GraphoGame but used it less frequently than expected. The reward system seemed to encourage the children to play longer sessions at the beginning of the training period, but this effect vanished after a few sessions. The level of challenge had no significant effect on children's engagement. The results suggest a need to investigate further the effectiveness of various game features in maintaining learner's engagement until the goals set for learning are achieved.     

Connecting the dots: Understanding the interrelated impacts of type,quality and children's awareness of design features and the mathematics content learning goals in digital math games and related learning outcomes

This study focused on an examination of how type, quality and children's awareness of design features in digital math games, along with an awareness of the mathematics goals of the game, were related to learning outcomes. We conducted a parallel conversion mixed methods study with 45 students in Grades 3 and 4 (ages 9–10). Students participated in clinical interviews using three digital math games. The results suggest a moderated mediation relationship in which the quality of the design features moderated the mediating impact of children's awareness of the game's design features, specifically when the child was aware of the mathematics content learning goal (MCLG) of the game. These findings show how important it is that design features are of high quality in a digital math game, and how this is intertwined with children's awareness of the features and the MCLG. When these variables intertwined in just the right way, the interactions between the children and the digital math game afforded mathematical learning growth.     

Gamified monetary reward designs: Offering certain versus chance-based rewards

To motivate visitors to engage with websites, e-tailers widely employ monetary rewards (e.g., vouchers, discounts) in their website designs. With advances in user interface technologies, many e-tailers have started to offer gamified monetary reward designs (MRDs), which require visitors to earn the monetary reward by playing a game, rather than simply claiming the reward. However, little is known about whether and why gamified MRDs engage visitors compared to their non-gamified counterpart. Even less is known about the effectiveness of gamified MRDs when providing certain or chance-based rewards, in that visitors do or do not know what reward they will gain for successfully performing in the game. Drawing on cognitive evaluation theory, we investigate gamified MRDs with certain or chance-based rewards and contrast them to non-gamified MRDs with certain rewards in user registration systems. Our results from a multi-method approach encompassing the complementary features of a randomised field experiment (N = 651) and a randomised online experiment (N = 330) demonstrate differential effects of the three investigated MRDs on user registration. Visitors encountering either type of gamified MRD are more likely to register than those encountering a non-gamified MRD. Moreover, gamified MRDs with chance-based rewards have the highest likelihood of user registrations. We also show that MRDs have distinct indirect effects on user registration via anticipated experiences of competence and sensation. Overall, the paper offers theoretical insights and practical guidance on how and why gamified MRDs are effective for e-tailers.     

Physiology-based affect recognition for computer-assisted intervention of children with Autism Spectrum Disorder

Generally, an experienced therapist continuously monitors the affective cues of the children with Autism Spectrum Disorders (ASD) and adjusts the course of the intervention accordingly. In this work, we address the problem of how to make the computer-based ASD intervention tools affect-sensitive by designing therapist-like affective models of the children with ASD based on their physiological responses. Two computer-based cognitive tasks are designed to elicit the affective states of liking, anxiety, and engagement that are considered important in autism intervention. A large set of physiological indices are investigated that may correlate with the above affective states of children with ASD. In order to have reliable reference points to link the physiological data to the affective states, the subjective reports of the affective states from a therapist, a parent, and the child himself/herself were collected and analyzed. A support vector machines (SVM)-based affective model yields reliable prediction with approximately 82.9% success when using the therapist's reports. This is the first time, to our knowledge, that the affective states of children with ASD have been experimentally detected via physiology-based affect recognition technique.     

Outcomes for design and learning when teenagers with autism codesign a serious game: A pilot study

Digital educational games research tends to lack ecological validity by not adequately taking into account the views and perspectives of children and young people with autism spectrum disorders (ASD). This paper is a pilot study that explores and analyses an academic‐based educational game that was co‐designed with and for young people with ASD. The serious game aims to help the players learn Geography‐specific knowledge and integrates several strategic features so that users can collaborate together against the computer or compete against each other. The educational game was evaluated over 5 sessions by 3 peer teams from 2 different special educational institutions, involving a total of 6 students with ASD. The participants were positive about their enjoyment, motivation, and social engagement. The results showed that the players' level of competitiveness not only influenced the experience within the game but also the interaction within the peer teams. The game mechanisms did help the participants with ASD increase their knowledge in Geography content. The main conclusion is that there are considerable benefits of including children with ASD in the design process and future research should explore more fully on how their involvement can enhance curriculum‐based learning as well as social engagement within the classroom.     

在加强型学习系统中用伪熵进行不确定性估计

加强型学习系统是一种与没有约束的，未知的环境相互作用的系统，学习系统的目标在大最大可能地获取累积奖励信号，这个奖励信号在有限，未知的生命周期由系统所处的环境中得到，对于一个加强型学习系统，困难之一在于奖励信号非常稀疏，尤其是对于只有时延信号的系统，已有的加强型学习方法以价值函数的形式贮存奖励信号，例如著名的Ｑ－学习。本文提出了一个基于状态的不生估计模型的方法，这个算法对有利用存贮于价值函数中的奖励     

Learning to Transform Service Instructions into Actions with Reinforcement Learning and Knowledge Base

In order to improve the learning ability of robots, we present a reinforcement learning approach with a knowledge base for mapping natural language instructions to executable action sequences. A simulated platform with physical engine is built as interactive environment. Based on the knowledge base, a reward function with immediate rewards and delayed rewards is designed to handle sparse reward problems. Also, a list of object states is produced by retrieving the knowledge base, as a standard to define the quality of action sequences. Experimental results demonstrate that our approach yields good performance on accuracy of action sequences production.     

强化学习算法中启发式回报函数的设计及其收敛性分析

(中国科学院沈阳自动化所机器人学重点实验室沈阳110016)     

An inclusive design approach for developing video games for children with Autism Spectrum Disorder

The efficacy of therapeutic treatments for Autism Spectrum Disorder is mainly associated with the treatment's intensity in terms of weekly hours. This has led mental health professionals to explore the use of video games to complement traditional treatments. However, major weaknesses have been found due to poor game design, which has failed to fulfill therapeutic objectives or to properly engage children. These weaknesses are typically characterized by the poor integration of knowledge from mental health experts, children's interests and designers' expertise. Starting from this necessity, we propose an inclusive design approach to develop therapeutic games. The method presents strategies to integrate the expertise of clinicians, contributions of children and experience of designers through a set of elicitation and merging techniques. The goal of this method is to design games that are effective in terms of therapeutic objectives and that are enjoyable for children. To describe this method, we present its application in the design and development of a Kinect-based game for high-functioning children with ASD called “Pico's Adventures”. This game aims at promoting social initiation in young children with autism. Findings from a first exploratory study with 10 children with ASD showed the effectiveness of the game in eliciting social initiation behaviors. This provides a first validation of the method. An essential aspect of the game's success was the use of elements and mechanics that were appealing for the children. As a result, we have identified effective design concepts and paths for further research on games for children with ASD.     

Multitouch tablet applications and activities to enhance the social skills of children with autism spectrum disorders

In spite of great improvements in early diagnosis and interventions, most children diagnosed with autism spectrum disorders (ASD) are unlikely to live independently when they reach adulthood. We have been conducting research on novel computer-based interventions with the goal of promoting social skills. Working with 26 children with ASD, their teachers, and other stakeholders, we have iteratively developed a set of activities based on applications that run on multitouch tablets. Our observations suggest these activities increased pro-social behaviors such as collaboration and coordination, augmented appreciation for social activities, and provided children with novel forms of expression.     

稀疏奖励下基于情感的异构多智能体强化学习

在强化学习中,当处于奖励分布稀疏的环境时,由于无法获得有效经验,智能体收敛速度和效率都会大幅下降.针对此类稀疏奖励,文中提出基于情感的异构多智能体强化学习方法.首先,建立基于个性的智能体情感模型,为异构多智能体提供激励机制,作为外部奖励的有效补充.然后,基于上述激励机制,融合深度确定性策略,提出稀疏奖励下基于内在情感激...     

Preschool children’s learning with technology at home

We produced case studies of fourteen families based on nine rounds of data collection during the period from June 2008 to October 2009. We focused on fourteen children who were three years old when our visits started and used an ecocultural approach to examine their experiences of learning and playing with technologies at home. The study describes i) which technologies children encounter at home, ii) how family practices influence children’s encounters with technology, and iii) what children are learning through their interactions with technology. We present a framework of four areas of learning that could be supported by technology: acquiring operational skills, extending knowledge and understanding of the world, developing dispositions to learn, and understanding the role of technology in everyday life.     

Analyzing and visualizing multiagent rewards in dynamic and stochastic domains

The ability to analyze the effectiveness of agent reward structures is critical to the successful design of multiagent learning algorithms. Though final system performance is the best indicator of the suitability of a given reward structure, it is often preferable to analyze the reward properties that lead to good system behavior (i.e., properties promoting coordination among the agents and providing agents with strong signal to noise ratios). This step is particularly helpful in continuous, dynamic, stochastic domains ill-suited to simple table backup schemes commonly used in TD(λ)/Q-learning where the effectiveness of the reward structure is difficult to distinguish from the effectiveness of the chosen learning algorithm. In this paper, we present a new reward evaluation method that provides a visualization of the tradeoff between the level of coordination among the agents and the difficulty of the learning problem each agent faces. This method is independent of the learning algorithm and is only a function of the problem domain and the agents’ reward structure. We use this reward property visualization method to determine an effective reward without performing extensive simulations. We then test this method in both a static and a dynamic multi-rover learning domain where the agents have continuous state spaces and take noisy actions (e.g., the agents’ movement decisions are not always carried out properly). Our results show that in the more difficult dynamic domain, the reward efficiency visualization method provides a two order of magnitude speedup in selecting good rewards, compared to running a full simulation. In addition, this method facilitates the design and analysis of new rewards tailored to the observational limitations of the domain, providing rewards that combine the best properties of traditional rewards.     

How do young children engage with mobile apps? Cognitive,psychomotor, and affective perspective

This paper reports on situations in which children engage with mobile apps to better understand how they learn through such interaction. The following two research questions were postulated to address the research purpose: i) What are the conditions that engage children with mobile apps? ii) How does learning take place during children's engagement with mobile apps? The study was carried out using a qualitative approach by observing young children's interactions when using mobile apps. A total of 18 pre-schoolers aged 4–6 years participated in the study. The observation sessions were video-recorded to unobtrusively observe the participants' interactions with 20 selected mobile apps. The data were analysed using a thematic approach to examining children's emergent behaviours when engaging with mobile apps to identify, generate code, and produce themes. The findings demonstrated three prominent conditions of children's learning engagement: collective sensory skill, emotional expression, and verbal expression. It is evident from the study that learning in this environment takes place through cognitive, psychomotor-based, and affective means. This study provides significant insight on how young children engage with mobile apps to articulate their design implications as well as general guidelines for selecting quality mobile apps to encourage engagement in home, classroom, and library use.     

Multimodal fusion for autonomous navigation via deep reinforcement learning with sparse rewards and hindsight experience replay

The multimodal perception of intelligent robots is essential for achieving collision-free and efficient navigation. Autonomous navigation is enormously challenging when perception is acquired using only vision or LiDAR sensor data due to the lack of complementary information from different sensors. This paper proposes a simple yet efficient deep reinforcement learning (DRL) with sparse rewards and hindsight experience replay (HER) to achieve multimodal navigation. By adopting the depth images and pseudo-LiDAR data generated by an RGB-D camera as input, a multimodal fusion scheme is used to enhance the perception of the surrounding environment compared to using a single sensor. To alleviate the misleading way for the agent to navigate with dense rewards, the sparse rewards are intended to identify its tasks. Additionally, the HER technique is introduced to address the sparse reward navigation issue for accelerating optimal policy learning. The results show that the proposed model achieves state-of-the-art performance in terms of success, crash, and timeout rates, as well as generalization capability.     

Future technology workshop: A collaborative method for the design of new learning technologies and activities

We describe the future technology workshop (FTW), a method whereby people with everyday knowledge or experience in a specific area of technology use (such as using digital cameras) envision and design the interactions between current and future technology and activity. Through a series of structured workshop sessions, participants collaborate to envisage future activities related to technology design; build models of the contexts of use for future technologies; act out scenarios of use for their models; re-conceive their scenarios in relation to present-day technologies; list problems with implementing the scenarios; explore the gap between current and future technology and activity; and end by listing requirements for future technology. The method has been used successfully with children and adults to explore new technology–activity systems, including interacting with digital photographs and informal science learning.