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).
@cclauss Hi! Thank you for pointing out the error! Actually this function is replaced by built-in function at corresponding sub-class of tdagent (like bcrp).
flake8 testing of https://github.com/ZhengyaoJiang/PGPortfolio on Python 3.6.3
$ flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics