“FIN Status Report 2016-11-21”版本间的差异

2016年11月21日 (一) 01:16的最后版本

People	Last Week	This Week
Yang Wang	Test drrl with 1min data and obtain good results. Find some problems in training, such as the fact that all the action are +1 or -1. It seems that it can be trained successful at a probability.	study the problems
Yuxin Zhang	Use 1min daily data for dqt and acquire good results. Design automated network establishing strategy. Read some papers about local minima in training neural networks.	Try to add factors as part of the input data. Implement experiments of drrl using 1min data.

@@ 第4行： / 第4行： @@
 |-
 | Yang Wang||
-Have a meeting with Quantitative Association and discuss things about cooperation.<br>
+Test drrl with 1min data and obtain good results.<br>
-Improve our platform<br>
+Find some problems in training, such as the fact that all the action are +1 or -1.<br>
-Read some papers about GAN<br>
+It seems that it can be trained successful at a probability.<br>
-Do some experiments and find some problems
 ||
-Analysis the problems of current model. <br>
+study the problems <br>
-try minute data
 |-
 | Yuxin Zhang||
-Try to use more suitable goals for DRRL.<br>
+Use 1min daily data for dqt and acquire good results.<br>
-Design automated simulation tests.<br>
+Design automated network establishing strategy.<br>
-Read some papers from ICLR2017.<br>
+Read some papers about local minima in training neural networks.<br>
 ||
-Find explanations for the experiment results.<br>
+Try to add factors as part of the input data.<br>
-Try different algorithms.
+Implement experiments of drrl using 1min data.
 |}