PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).
GNU General Public License v3.0
1.73k
stars
748
forks
source link
problems about state representation `datametrices.py` #106
In marketdata/datametrices.py, line 172, there is a function get_submatrix(self, ind). This function is suppose to gives the state representation for a given time index ind. Here, the state should be a history price(or return) between time period [ind-window_size, ind]. However, in get_submatrix, we have
In
marketdata/datametrices.py
, line172
, there is a functionget_submatrix(self, ind)
. This function is suppose to gives the state representation for a given time indexind
. Here, the state should be a history price(or return) between time period[ind-window_size, ind]
. However, inget_submatrix
, we havewhich means it use future price(or return) to represent current state at time
ind
. Is there any explanation about this problem ?