scholarly journals Applying and Augmenting Deep Reinforcement Learning in Serious Games through Interaction

Author(s):  
Aline Dobrovsky ◽  
Uwe M. Borghoff ◽  
Marko Hofmann

Serious games belong to the most important future e-learning trends and are frequently used in recruitment and training. Their development, however, is still a demanding and tedious process, especially when regarding reasonable non-player character behaviour. Serious games can generally profit from diverse, adaptive behaviour to increase learning effectiveness. Deep reinforcement learning has already shown considerable results in automatically generating successful AI behaviour, but its past applications were mainly focused on optimization and short-horizon games. To expand the underlying ideas to serious games, we introduce a new approach of augmenting the application of deep reinforcement learning methods by interactively making use of domain experts’ knowledge to guide the learning process. Thereby, we aim to establish a synergistic combination of experts and emergent cognitive systems to create adaptive and more human behaviour. We call this approach interactive deep reinforcement learning and point out important aspects regarding realization within a novel framework.

2021 ◽  
Vol 11 (1) ◽  
pp. 6637-6644
Author(s):  
H. El Fazazi ◽  
M. Elgarej ◽  
M. Qbadou ◽  
K. Mansouri

Adaptive e-learning systems are created to facilitate the learning process. These systems are able to suggest the student the most suitable pedagogical strategy and to extract the information and characteristics of the learners. A multi-agent system is a collection of organized and independent agents that communicate with each other to resolve a problem or complete a well-defined objective. These agents are always in communication and they can be homogeneous or heterogeneous and may or may not have common objectives. The application of the multi-agent approach in adaptive e-learning systems can enhance the learning process quality by customizing the contents to students’ needs. The agents in these systems collaborate to provide a personalized learning experience. In this paper, a design of an adaptative e-learning system based on a multi-agent approach and reinforcement learning is presented. The main objective of this system is the recommendation to the students of a learning path that meets their characteristics and preferences using the Q-learning algorithm. The proposed system is focused on three principal characteristics, the learning style according to the Felder-Silverman learning style model, the knowledge level, and the student's possible disabilities. Three types of disabilities were taken into account, namely hearing impairments, visual impairments, and dyslexia. The system will be able to provide the students with a sequence of learning objects that matches their profiles for a personalized learning experience.


Author(s):  
Lamia Mahnane ◽  
Mohamed Hafidi

Adaptive E-learning Hypermedia Systems (AEHS) are an innovative approach to a web learning experience delivery. They try to solve main shortcomings of classical hypermedia e-learning applications: “one-size-fits-all” approach and “lost-in-hyperspace” phenomena by adapting the learning content and its presentation to needs, goals, thinking styles and learning styles of every individual learner. This paper outlines a new approach to automatically detect learner's thinking and learning styles, and taking into account that thinking and learning styles may change during the learning process in an unexpected and unpredictable way. The authors' approach is based on the Felder Learning Styles Model and Hermann thinking styles model.


Author(s):  
Daniel Burgos ◽  
Christof van Nimwegen

Serious games are suitable for learning. They are a good environment for improving the learning experience. As a key part of this setting, feedback becomes a useful support for decision making and can reinforce the learning process in order to achieve certain objectives. Destination feedback allows users to draw on strategies and improve skills. However, too much feedback can make the learner too dependant on external advice when taking the next action, resulting in a weaker strategy and a lower performance. In this chapter the authors introduce a conceptual approach to feedback in E-Learning with serious games; how useful or harmful it can be in a learning process. They describe a case study carried out with a simulation of an educational planning task. The authors studied the performance of 43 learners who had, or did not have, visual destination feedback in a problem solving task. They conclude that in this context, too much assistance can be counterproductive.


2020 ◽  
Vol 9 (2) ◽  
pp. 182-195
Author(s):  
Wida Yanto

Abstract This research was based on the teaching and learning process now in the education and training field which most of it still tends to be done conventionally. Learning through E-learning can overcome the constraints of space and time. Widyaiswara (Instructor) and training participants can make the learning process both synchronous (direct), and asynchronous (indirectly) through the virtual world. This study is intended to describe the influence of LMS Schoology in improving the learning outcomes of English Training participants in Religious Education and Training Center (BDK) Surabaya. Formulation of the problem “Is there a significant and positive influence on the use of LMS Schoology on Improving Learning Outcomes of English Teacher Training Participants?” The research method used is pre-experimental one group pretest-postets with regression analysis. Regression analysis is used to find out how much influence the independent variable has on the increase in the dependent variable. The results showed that after teaching and learning process was carried out with the LMS Schoology application media there is a significant and positive influence on the use of LMS Schoology to increase the learning outcomes of English Teacher Training participants and the amount of the influence of the LMS Schoology usage variable on the increase participant learning outcomes is 77.4%. That is, the effect of LMS Schoology on the learning outcomes of training participants is 77.4%.   Keywords: E-learning, LMS Schoology, learning outcomes


2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
Francesco Ricciardi ◽  
Lucio Tommaso De Paolis

Education of healthcare professionals is of primary importance for patient safety. In some health related professions, education and training have to be practiced during the entire working period and not only limited to school years. The use of new technology such as virtual reality and e-learning brings new possibilities with significant improvement in learning outcomes. Serious gaming describes a technology that can educate and train while entertaining users. This type of training can be very useful for health professions because it improves learning outcomes creating a learner oriented approach and providing a stealth mode of teaching. In some fields it represents an ideal instrument for continuous health professions education also in terms of costs because it is cheaper than traditional training methods that use cadavers or mannequins. In this paper we make a scoping review of serious games developed for health professions and health related fields in order to understand if they are useful tools for health related fields training. Many papers confirmed that serious gaming is a useful technology that improves learning and skills development for health professionals.


2011 ◽  
pp. 1048-1059
Author(s):  
Daniel Burgos ◽  
Christof van Nimwegen

Serious games are suitable for learning. They are a good environment for improving the learning experience. As a key part of this setting, feedback becomes a useful support for decision making and can reinforce the learning process in order to achieve certain objectives. Destination feedback allows users to draw on strategies and improve skills. However, too much feedback can make the learner too dependant on external advice when taking the next action, resulting in a weaker strategy and a lower performance. In this chapter the authors introduce a conceptual approach to feedback in E-Learning with serious games; how useful or harmful it can be in a learning process. They describe a case study carried out with a simulation of an educational planning task. The authors studied the performance of 43 learners who had, or did not have, visual destination feedback in a problem solving task. They conclude that in this context, too much assistance can be counterproductive.


2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Bo Xin ◽  
Haixu Yu ◽  
You Qin ◽  
Qing Tang ◽  
Zhangqing Zhu

The training process analysis and termination condition of the training process of a Reinforcement Learning (RL) system have always been the key issues to train an RL agent. In this paper, a new approach based on State Entropy and Exploration Entropy is proposed to analyse the training process. The concept of State Entropy is used to denote the uncertainty for an RL agent to select the action at every state that the agent will traverse, while the Exploration Entropy denotes the action selection uncertainty of the whole system. Actually, the action selection uncertainty of a certain state or the whole system reflects the degree of exploration and the stage of the learning process for an agent. The Exploration Entropy is a new criterion to analyse and manage the training process of RL. The theoretical analysis and experiment results illustrate that the curve of Exploration Entropy contains more information than the existing analytical methods.


2009 ◽  
Vol 3 (5-6) ◽  
pp. 21-24
Author(s):  
Péter Lengyel ◽  
Miklós Herdon

Learning Design has the potential to revolutionize e-learning by capturing the process of education, rather than simply content. By describing sequences of collaborative learning activities, Learning Design offers a new approach to re-use in e-learning. E-learning has a well developed approach to the creation and sequencing of content-based, single learner, self-paced learning objects.While definitions of Learning Design vary, the main elements tend to include greater focus on context dimensions of e-learning, a more activity based view of e-learning, and greater recognition of the role of multi-learner environments. While Learning Design does not exclude single learner, self-paced modes of elearning, it draws attention to a wider range of collaborative e-learning approaches in addition to single learner approaches. This paper shows an example, which is applied to speciality of economic and rural development agricultural engineer at University of Debrecen and its implementation in the Learning Activity Management System. We created a learning design was implemented at this speciality with LAMS, which is a learning design editing and play back tool that puts the learning process, rather than collections of content, at the heart of e-learning.


2018 ◽  
pp. 49-57
Author(s):  
N. A. Gluzman

In the modern educational space regarding the realities of the information society special importance is attached to issues related to the provision of a high level of informatization of education, which implies teachers’ mastering the necessary competencies and the ability to introduce e-learning resources into educational and training practice. Adobe Flash as one of the platforms for creating web applications and multimedia presentations enjoys greatest popularity with users including teachers. However, in connection with the announcement of discontinuing Adobe Flash support in 2020, the issue of choosing an analog to create web applications and presentations for use in teaching purposes is becoming particularly relevant. The article provides a comprehensive analysis of developing electronic educational resources by teachers using Adobe Flash and HTML5 for teaching math in primary school.


2015 ◽  
Vol 6 (9) ◽  
pp. 1606-1612
Author(s):  
Zaydoon Mohammad Hatamleh ◽  
Eslam Najim Badran ◽  
Bilal Mohammad Hatamleh

Sign in / Sign up

Export Citation Format

Share Document