wassname/rl-portfolio-management
1
0
Fork 0
mirror of https://github.com/wassname/rl-portfolio-management.git synced 2026-06-27 16:46:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme with refs to more recent work

Browse Source
This commit is contained in:
Mike Clark
2019-05-25 03:03:20 +00:00
committed by GitHub
parent 2e0246f812
commit ca76af8df0
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
readme.md
+4 -1
View File
@@ -1,6 +1,9 @@
Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" by [Jiang et. al. 2017](https://arxiv.org/abs/1706.10059) [1].
**Note: the paper's authors have put [the official code for the paper up and it works well](https://github.com/ZhengyaoJiang/PGPortfolio)**
**Note2 (20190525):** vermouth1992 improved this environment during their final project, I reccomend you start with their [repo](https://github.com/vermouth1992/drl-portfolio-management). Also check out the [sagemaker tutorial](https://github.com/awslabs/amazon-sagemaker-examples/blob/master/reinforcement_learning/rl_portfolio_management_coach_customEnv/rl_portfolio_management_coach_customEnv.ipynb) which is based on vermouth1992's work.
Note1 (2018): the paper's authors have put [the official code for the paper up and it works well](https://github.com/ZhengyaoJiang/PGPortfolio)
tl;dr I managed to get 8% growth on training data, but it disapeared on test data. So I couldn't replicate it. However, RL papers can be very difficult to replicate due to bugs, framework differences, and hyperparameter sensistivity