Search

Resource limitations make it hard to provide all students with one of the most effective educational interventions: personalized instruction. Reinforcement learning could be a key tool to reduce the development cost and improve the effectiveness of intelligent tutoring software that aims to provide the right support, at the right time, to a student. Here we illustrate that deep reinforcement learning can be used to provide adaptive pedagogical support to students learning about the concept of volume in a narrative storyline software. Using explainable artificial intelligence tools, we extracted interpretable insights about the pedagogical policy learned and demonstrated that the resulting policy had similar performance in a different student population. Most importantly, in both studies, the reinforcement-learning narrative system had the largest benefit for those students with the lowest initial pretest scores, suggesting the opportunity for AI to adapt and provide support for those most in need., Comment: 23 pages. Under review

© 2019 A new direction of risk assessment research in grassland fire management is data-driven prediction, in which data are collected from particular regions. Since some regions have rich datasets that can easily generate knowledge for risk prediction, and some have no data available, this study addresses how we can leverage the knowledge learned from one grassland risk assessment to assist with a current assessment task. In this paper, we first introduce the transfer learning methodology to map and update risk maps in grassland fire management, and we propose a new grassland fire risk analysis method. In this study, two major grassland areas (Xilingol and Hulunbuir) in northern China are selected as the study areas, and five representative indicators (features) are extracted from grassland fuel, fire climate, accessibility, human and social economy. Taking Xilingol as the source domain (where sufficient labelled data are available) and Hulunbuir as the target domain (which contains insufficient data but requires risk assessment/prediction), we then establish the mapping relationship between grassland fire indicators and the degrees of grassland fire risk by using a transfer learning method. Finally, the fire risk in the Hulunbuir grassland is assessed using the transfer learning method. Experiments show that the prediction accuracy reached 87.5% by using the transfer learning method, representing a significant increase over existing methods.