“FIN Status Report 2017-3-6”版本间的差异
来自cslt Wiki
| 第4行： | 第4行： | ||
|- | |- | ||
| Yang Wang|| | | Yang Wang|| | ||
| − | + | train the model with different stock set, which consist of 10 stocks belonging to 10 industries. <br> | |
digitize the asset and set it as reward, which make the training and the target more mathing<br> | digitize the asset and set it as reward, which make the training and the target more mathing<br> | ||
| − | clip gradients, which stabilizes the training<br> | + | clip the gradients, which stabilizes the training<br> |
| − | + | randomize the goal. Its impact remains to be seen<br> | |
|| | || | ||
2017年3月9日 (四) 04:47的版本
| People | Last Week | This Week |
|---|---|---|
| Yang Wang |
train the model with different stock set, which consist of 10 stocks belonging to 10 industries. |
do more test |
| Yuxin Zhang |
Try to use Pyalgotrading to test the algorithm. |
Test the ddpg algorithm with stock selection algorithm. |
| Yaodong Wang | Learn git, pyalgotrade ,CNN and other models | help do test |
| Tongzheng Ren | Implement the backtesting strategy for latest use. Help refactoring part of the data process module. |
Test the new strategy. |
