No abstract

Photocatalytic hydrogen evolution from water has triggered an intensive search for metal-free semiconducting photocatalysts. However, traditional semiconducting materials suffer from limited hydrogen evolution efficiency owing to low intrinsic electron transfer, rapid recombination of photogenerated carriers, and lack of artificial microstructure. Herein, we report a metal-free half-metallic carbon nitride for highly efficient photocatalytic hydrogen evolution. The introduced half-metallic features not only effectively facilitate carrier transfer but also provide more active sites for hydrogen evolution reaction. The nanosheets incorporated into a micro grid mode resonance structure via in situ pyrolysis of ionic liquid, which show further enhanced photoelectronic coupling and entire solar energy exploitation, boosts the hydrogen evolution rate reach up to 1009 μmol g−1 h−1. Our findings propose a strategy for micro-structural regulations of half-metallic carbon nitride material, and meanwhile the fundamentals provide inspirations for the steering of electron transfer and solar energy absorption in electrocatalysis, photoelectrocatalysis, and photovoltaic cells.

No abstract

In E-commerce platforms such as Amazon and TaoBao, ranking items in a search session is a typical multi-step decision-making problem. Learning to rank (LTR) methods have been widely applied to ranking problems. However, such methods often consider different ranking steps in a session to be independent, which conversely may be highly correlated to each other. For better utilizing the correlation between different ranking steps, in this paper, we propose to use reinforcement learning (RL) to learn an optimal ranking policy which maximizes the expected accumulative rewards in a search session. Firstly, we formally define the concept of search session Markov decision process (SSMDP) to formulate the multistep ranking problem. Secondly, we analyze the property of SSMDP and theoretically prove the necessity of maximizing accumulative rewards. Lastly, we propose a novel policy gradient algorithm for learning an optimal ranking policy, which is able to deal with the problem of high reward variance and unbalanced reward distribution of an SSMDP. Experiments are conducted in simulation and TaoBao search engine. The results demonstrate that our algorithm performs much better than the state-of-the-art LTR methods, with more than 40% and 30% growth of total transaction amount in the simulation and the real application, respectively. KEYWORDS reinforcement learning; online learning to rank; policy gradient ACM Reference Format: