FIN Status Report 2017-3-6

People	Last Week	This Week
Yang Wang	training with different stock set, which consist of 10 stocks belonging to 10 industries. digitize the asset and set it as reward, which make the training and the target more mathing clip gradients, which stabilizes the training random goal. Its impact remains to be seen	do more test
Yuxin Zhang	Try to add convolutional layers to the ddpg model. Use more suitable reward function.	Use Pyalgotrading to test the algorithm. Start to develop algorithm for in-day market timing.
Yaodong Wang	Deal with the database and learn pyalgotrade	help do tests
Tongzheng Ren	Implement the backtesting strategy for latest use. Help refactoring part of the data process module.	Test the new strategy.