17 August 2017 in IEEE Transactions on Vehicular Technology
Licensed-assisted access (LAA) of the long term evolution (LTE) has been standardized by the Third Generation Partnership Project (3GPP) in Release 13 to address the urgent issues of ever-increasing traffic demands in cellular systems. However, challenges arise for the efficient coexistence of Wi-Fi and LAA in the same unlicensed spectrum. In this paper, the impact of LAA's energy detection thresholds on such coexistence are investigated from the perspective of collisions occurring during downlink transmissions. To facilitate the efficient coexistence of Wi-Fi and LAA, a distributed algorithm is proposed to adaptively change the energy detection thresholds of LAA per user or per base station, so that the system encourages more concurrent transmissions without introducing too many collisions. Simulation results validate the effectiveness of the proposed adaptive algorithm.
19 August 2024 in ACM Transactions on Information Systems
Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn the recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this article, we address the cold-start challenge in the RL-based recommender systems by proposing a novel context-aware offline meta-level model-based RL approach for user adaptation. Our proposed approach learns to infer each user's preference with a user context variable that enables recommendation systems to better adapt to new users with limited contextual information. To improve adaptation efficiency, our approach learns to recover the user choice function and reward from limited contextual information through an inverse RL method, which is used to assist the training of a meta-level recommendation agent. To avoid the need for online interaction, the proposed method is trained using historically collected offline data. Moreover, to tackle the challenge of offline policy training, we introduce a mutual information constraint between the user model and recommendation agent. Evaluation results show the superiority of our developed offline policy learning method when adapting to new users with limited contextual information. In addition, we provide a theoretical analysis of the recommendation performance bound.