forex-trading-automation-with-deep-reinforcement-learning

Forex Trading Automation with PPO, ACKTR, DDPG, TD3 and Ensemble Strategy

https://github.com/tomatoft/forex-trading-automation-with-deep-reinforcement-learning

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.7%) to scientific vocabulary

Keywords

artificial-intelligence cs106-uit deep-reinforcement-learning ds304-uit forex-trading multi-agent-systems
Last synced: 6 months ago · JSON representation ·

Repository

Forex Trading Automation with PPO, ACKTR, DDPG, TD3 and Ensemble Strategy

Basic Info
Statistics
  • Stars: 35
  • Watchers: 2
  • Forks: 8
  • Open Issues: 1
  • Releases: 0
Topics
artificial-intelligence cs106-uit deep-reinforcement-learning ds304-uit forex-trading multi-agent-systems
Created over 3 years ago · Last pushed almost 3 years ago
Metadata Files
Readme Citation

README.md

Forex Trading Automation with Deep Reinforcement Learning

How to run

You can use the .ipynb file to run the project

Clone the project

git clone https://github.com/TomatoFT/Forex-Trading-Automation-with-Deep-Reinforcement-Learning cd Forex-Trading-Automation-with-Deep-Reinforcement-Learning

Create the Anaconda Environment

conda create --name Forex conda activate Forex

Install some package and dependancies

sudo apt-get update && sudo apt-get install cmake libopenmpi-dev python3-dev zlib1g-dev libgl1-mesa-glx conda install python=3.7 anaconda=custom pip install -r requirements.txt

Run Deep Reinforcement learning methods

python run_DRL.py

Exit the Anaconda Environment

conda deactivate

Publication

We use this project to have the publication in RIVF 2022 conference. For more about the methods or the implementation of the project you can read the paper with information below.

@INPROCEEDINGS{10013861, author={Chau, Tan and Nguyen, Minh-Tri and Ngo, Duc-Vu and Nguyen, Anh-Duc T. and Do, Trong-Hop}, booktitle={2022 RIVF International Conference on Computing and Communication Technologies (RIVF)}, title={Deep Reinforcement Learning methods for Automation Forex Trading}, year={2022}, volume={}, number={}, pages={671-676}, doi={10.1109/RIVF55975.2022.10013861}}

NOTICE

In Janary 9 2023, I known that Google Colab had suspended the Tensorflow 1.x. So the baseline on Colab file is not running anyways. To run this, you can use command in the baseline to deploy on other place (I recommend you to use Docker). Or you can update the whole codes to transform from tensorflow 1 to tensorflow 2. If you want to have any contributed, you can make an request and I will appreciate if you do that

Feel free to clone my code and I will appreciate if you improve it

Owner

  • Name: Châu Tấn
  • Login: TomatoFT
  • Kind: user
  • Location: Vietnam
  • Company: UIT-VNUHCM

🧑‍🎓 Study Data Science at UIT

Citation (CITATION.cff)

@INPROCEEDINGS{10013861,
  author={Chau, Tan and Nguyen, Minh-Tri and Ngo, Duc-Vu and Nguyen, Anh-Duc T. and Do, Trong-Hop},
  booktitle={2022 RIVF International Conference on Computing and Communication Technologies (RIVF)}, 
  title={Deep Reinforcement Learning methods for Automation Forex Trading}, 
  year={2022},
  volume={},
  number={},
  pages={671-676},
  doi={10.1109/RIVF55975.2022.10013861}}

GitHub Events

Total
  • Watch event: 6
  • Fork event: 4
Last Year
  • Watch event: 6
  • Fork event: 4

Dependencies

requirements.txt pypi
  • gym ==0.15.3
  • joblib ==0.15.1
  • matplotlib ==3.2.1
  • numpy ==1.16.4
  • pandas ==1.0.3
  • pytest >=5.3.2,<6.0.0
  • scikit-learn ==0.21.0
  • setuptools >=41.4.0,<42.0.0
  • stable-baselines *
  • stockstats *
  • tensorflow ==1.15.4
  • wheel >=0.33.6,<0.34.0