%PDF-1.5
%
1 0 obj
<>stream
application/pdfIEEEIEEE Communications Letters; ;PP;99;10.1109/LCOMM.2019.2922961Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network SlicingChen QiYuxiu HuaRongpeng LiZhifeng ZhaoHonggang Zhang
IEEE Communications Letters199PP10.1109/LCOMM.2019.29229611
endstream
endobj
2 0 obj
<>/Metadata 1 0 R/Pages 6 0 R>>
endobj
3 0 obj
<>
endobj
4 0 obj
<>stream
xS(T e
endstream
endobj
5 0 obj
<>stream
xST %
endstream
endobj
6 0 obj
<>
endobj
7 0 obj
<>>>/MediaBox[0.0 0.0 612.0 792.0]/QInserted true>>
endobj
8 0 obj
<>>>/MediaBox[0 0 612 792]/QInserted true>>
endobj
9 0 obj
<>/ProcSet[/PDF/Text]/Font<>>>/MediaBox[0 0 612 792]/QInserted true>>
endobj
10 0 obj
<>/ProcSet[/PDF/Text]/Font<>>>/MediaBox[0 0 612 792]/QInserted true>>
endobj
11 0 obj
<>/ProcSet[/PDF/Text]/Font<>>>/MediaBox[0 0 612 792]/QInserted true>>
endobj
12 0 obj
<>stream
HWn}'G+~1! 8[Iew Ry ltwԩn3[;pp&n?+k~pvqf~27v?|ð|}ye}~:{|-8va~f|8|۷ovٌϻOI|}x?wOχ/nx|OOc7:x^aF`އ~w/`~x<
>lA|eh
^6p wo?_v |^|sqxӧuEat^i>4\9L#5BhȺRʏ&8==?>