http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Action-Selection Strategy Insensitive to Parameter-Settings in Reinforcement Learning
Kenji Ono,Kazunori Iwata,Akira Hayashi 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8
Markov decision processes are one of the most popular frameworks for reinforcement learning. The entropy of probability density functions of Markv decision processes is referred to as the stochastic complexity. The stochastic complexity is helpful for tuning the parameters of an action-selection strategy to alleviate the exploration-exploitation dilemma. In this paper, we improve an action-selection strategy to make it insensitive to parameter-settings by using the stochastic complexity. This gives better policies for alleviating the above dilemma in most parameter-settings.
Ohkubo, Kei,Mizushima, Kentaro,Iwata, Ryosuke,Souma, Kazunori,Suzuki, Nobuo,Fukuzumi, Shunichi Royal Society of Chemistry 2010 Chemical communications Vol.46 No.4
<P>Photooxygenation of <I>p</I>-xylene by oxygen occurs efficiently under photoirradiation of 9-mesityl-2,7,10-trimethylacridinium ion (Me<SUB>2</SUB>Acr<SUP>+</SUP>–Mes) to yield <I>p</I>-tolualdehyde and hydrogen peroxide, which is initiated <I>via</I> photoinduced electron transfer of Me<SUB>2</SUB>Acr<SUP>+</SUP>–Mes to produce the electron-transfer state.</P> <P>Graphic Abstract</P><P>Photooxygenation of <I>p</I>-xylene by oxygen occurs efficiently under photoirradiation of mesitylacridinium in an O<SUB>2</SUB>-saturated acetonitrile solution to yield <I>p</I>-tolualdehyde and hydrogen peroxide. <IMG SRC='http://pubs.rsc.org/services/images/RSCpubs.ePlatform.Service.FreeContent.ImageService.svc/ImageService/image/GA?id=b920606j'> </P>