Continuous-Time Decision Transformer for Healthcare Applications.

Offline reinforcement learning (RL) is a promising approach for training intelligent medical agents to learn treatment policies and assist decision making in many healthcare applications, such as scheduling clinical visits and assigning dosages for patients with chronic conditions. In this paper, we investigate the potential usefulness of Decision Transformer (Chen et al., 2021)-a new offline RL paradigm-in medical domains where decision making in continuous time is desired. As Decision Transformer only handles discrete-time (or turn-based) sequential decision making scenarios, we generalize it to Continuous-Time Decision Transformer that not only considers the past clinical measurements and treatments but also the timings of previous visits, and learns to suggest the timings of future visits as well as the treatment plan at each visit. Extensive experiments on synthetic datasets and simulators motivated by real-world medical applications demonstrate that Continuous-Time Decision Transformer is able to outperform competitors and has clinical utility in terms of improving patients' health and prolonging their survival by learning high-performance policies from logged data generated using policies of different levels of quality.

A Design Strategy for Energy-Efficient Rural Houses in Severe Cold Regions.

In the past decade, Chinese urban areas have seen rapid development, and rural areas are becoming the next construction hotspot. The development of rural buildings in China has lagged behind urban development, and there is a lack of energy-efficient rural buildings. Rural houses in severe cold regions have the characteristics of large energy exchange, a long heating cycle, and low construction costs. Energy consumption is a crucial issue for rural houses in severe cold regions. How to balance the energy efficiency and building cost become a crucial problem. To solve this problem, we investigate the energy consumption of rural housing in cold regions, using Longquan Village in Heilongjiang Province, northeast China, as a case study. A low-energy design framework is established that considers the spatial layout, building type, enclosure system, and heating system. With the support of project funds, a demonstration house is constructed, and the energy savings performance of the building is investigated during the heating period. The results indicate that the energy savings rate of the demonstration house is 66%. The demonstration building enables local residents to learn construction methods for low-energy houses and promotes energy efficiency.