FIN Status Report 2016-10-31 - 版本历史

2016年10月31日 (一) 07:51 Wangyang

2016-10-31T07:51:05Z

2016年10月31日 (一) 02:00 Wangyang

2016-10-31T02:00:21Z

2016年10月31日 (一) 01:59 Wangyang

2016-10-31T01:59:56Z

2016年10月31日 (一) 01:59 Wangyang

2016-10-31T01:59:39Z

2016年10月31日 (一) 01:39 Zhangyuxin

2016-10-31T01:39:28Z

Zhangyuxin：以“ {| class="wikitable" !People !! Last Week !! This Week |- | Yang Wang|| find some problem in DQN and DDPG :
the stock is a Markov process instead of a decisio...”为内容创建页面

2016-10-31T01:03:41Z

以“ {| class="wikitable" !People !! Last Week !! This Week |- | Yang Wang|| find some problem in DQN and DDPG : the stock is a Markov process instead of a decisio...”为内容创建页面

新页面

{| class="wikitable"
!People !! Last Week !! This Week

|-
| Yang Wang||
find some problem in DQN and DDPG : 
the stock is a Markov process instead of a decision Markov process. 
implement the recurrent reinforcement learning algorithm.
||
do some experiments with DRRL.
|-
| Yuxin Zhang||
Read programs created by Yang Wang : DQN DRRL. 
Discuss the current bottlenecks of the algorithms and possible ways to break them. 
Read papers related to using rnn for trading.
||
try to demonstrate if DRRL works well (or at least if it's better than DQN).

|}

@@ 第6行： / 第6行： @@
 | Yang Wang||
 Do some experiments with DRRL. <br>
-Discuss with Yuxin Zhang about how to modified my code.
+Discuss with Yuxin Zhang about how to modify my code.
 ||

@@ 第9行： / 第9行： @@
 ||
-Do some survey about quantitative finance and arrange some tasks for our group.
+Do some survey about quantitative finance and arrange some tasks for our group. <br>
 Try to improve DRRL.
 |-

@@ 第5行： / 第5行： @@
 |-
 | Yang Wang||
-Do some experiments with DRRL.
+Do some experiments with DRRL. <br>
 Discuss with Yuxin Zhang about how to modified my code.

@@ 第5行： / 第5行： @@
 |-
 | Yang Wang||
-find some problem in DQN and DDPG :<br>
+Do some experiments with DRRL.
-the stock is a Markov process instead of a decision Markov process. <br>
+Discuss with Yuxin Zhang about how to modified my code.
-implement the recurrent reinforcement learning algorithm.
 ||
-do some experiments with DRRL.
+Do some survey about quantitative finance and arrange some tasks for our group.
 |-
 | Yuxin Zhang||

@@ 第12行： / 第12行： @@
 |-
 | Yuxin Zhang||
-Read programs created by Yang Wang : DQN DRRL. <br>
+Add normalization to the input data and get better experiment results. <br>
-Discuss the current bottlenecks of the algorithms and possible ways to break them.<br>
+Try different values of parameters and find more suitable settings.<br>
-Read papers related to using rnn for trading.
+Use multiple stocks for training to improve the performance of the algorithm.
 ||
-try to demonstrate if DRRL works well (or at least if it's better than DQN).
+Try to use high frequency stock data as inputs.
 |}

FIN Status Report 2016-10-31 - 版本历史

2016年10月31日 (一) 07:51 Wangyang

2016年10月31日 (一) 02:00 Wangyang

2016年10月31日 (一) 01:59 Wangyang

2016年10月31日 (一) 01:59 Wangyang

2016年10月31日 (一) 01:39 Zhangyuxin

Zhangyuxin：以“ {| class="wikitable" !People !! Last Week !! This Week |- | Yang Wang|| find some problem in DQN and DDPG : the stock is a Markov process instead of a decisio...”为内容创建页面

Zhangyuxin：以“ {| class="wikitable" !People !! Last Week !! This Week |- | Yang Wang|| find some problem in DQN and DDPG :
the stock is a Markov process instead of a decisio...”为内容创建页面