A Multi-Agent Deep Reinforcement Learning-Based Popular Content Distribution Scheme in Vehicular Networks.

The Internet of Vehicles (IoV) enables vehicular data services and applications through vehicle-to-everything (V2X) communications. One of the key services provided by IoV is popular content distribution (PCD), which aims to quickly deliver popular content that most vehicles request. However, it is challenging for vehicles to receive the complete popular content from roadside units (RSUs) due to their mobility and the RSUs' constrained coverage. The collaboration of vehicles via vehicle-to-vehicle (V2V) communications is an effective solution to assist more vehicles to obtain the entire popular content at a lower time cost. To this end, we propose a multi-agent deep reinforcement learning (MADRL)-based popular content distribution scheme in vehicular networks, where each vehicle deploys an MADRL agent that learns to choose the appropriate data transmission policy. To reduce the complexity of the MADRL-based algorithm, a vehicle clustering algorithm based on spectral clustering is provided to divide all vehicles in the V2V phase into groups, so that only vehicles within the same group exchange data. Then the multi-agent proximal policy optimization (MAPPO) algorithm is used to train the agent. We introduce the self-attention mechanism when constructing the neural network for the MADRL to help the agent accurately represent the environment and make decisions. Furthermore, the invalid action masking technique is utilized to prevent the agent from taking invalid actions, accelerating the training process of the agent. Finally, experimental results are shown and a comprehensive comparison is provided, which demonstrates that our MADRL-PCD scheme outperforms both the coalition game-based scheme and the greedy strategy-based scheme, achieving a higher PCD efficiency and a lower transmission delay.

Multitrend Conditional Value at Risk for Portfolio Optimization.

Trend representation has been attracting more and more attention recently in portfolio optimization (PO) via machine learning methods. It adopts concepts and phenomena from the field of empirical and behavioral finance when little prior knowledge is obtained or strict statistical assumptions cannot be guaranteed. It is used mostly in estimating the expected asset returns, but hardly in measuring risk. To fill this gap, we propose a novel multitrend conditional value at risk (MT-CVaR), which embeds multiple trends and their influences in CVaR. Besides, we propose a novel PO model with this MT-CVaR as the risk metric and then design a solving algorithm based on the interior point method to compute the portfolio. Extensive experiments on six benchmark datasets from diverse financial markets with different frequencies show that MT-CVaR achieves the state-of-the-art investing performance and risk management.

Students' experience of online learning during the COVID-19 pandemic: A province-wide survey study.

Online learning is currently adopted by educational institutions worldwide to provide students with ongoing education during the COVID-19 pandemic. Even though online learning research has been advancing in uncovering student experiences in various settings (i.e., tertiary, adult, and professional education), very little progress has been achieved in understanding the experience of the K-12 student population, especially when narrowed down to different school-year segments (i.e., primary and secondary school students). This study explores how students at different stages of their K-12 education reacted to the mandatory full-time online learning during the COVID-19 pandemic. For this purpose, we conducted a province-wide survey study in which the online learning experience of 1,170,769 Chinese students was collected from the Guangdong Province of China. We performed cross-tabulation and Chi-square analysis to compare students' online learning conditions, experiences, and expectations. Results from this survey study provide evidence that students' online learning experiences are significantly different across school years. Foremost, policy implications were made to advise government authorises and schools on improving the delivery of online learning, and potential directions were identified for future research into K-12 online learning.