Trading with recurrent actor-critic reinforcement learning
Note: Sorry for misleading naming - please use A3Ctrading.py for training and testtrading.py for testing.
Trading with recurrent actor-critic reinforcement learning - check paper and more detailed old report
config.py
This file contains all the pathes and gloabal variables to be set up
After setting
config.pyplease run this file to download and preprocess the data need for training and evaluation
trader_gym.py
OpenAI.gym-like environment class
A3C_class.py
This file is containing
AC_network,
Workerand
Test_Workerclasses
A3C_training.py
Run this file, preferrable in
tmux. During training it will create files in
tensorboard_dirand in
model_dir
A3C_testing.ipynb
Jupyter notebookcontains all for picturing
@article{ponomarev2019using, title={Using Reinforcement Learning in the Algorithmic Trading Problem}, author={Ponomarev, ES and Oseledets, IV and Cichocki, AS}, journal={Journal of Communications Technology and Electronics}, volume={64}, number={12}, pages={1450--1457}, year={2019}, publisher={Springer} }