https://github.com/filangelos/qtrader
Reinforcement Learning for Portfolio Management
https://github.com/filangelos/qtrader
algorithmic-trading python q-learning recurrent-neural-networks reinforcement-learning
Last synced: about 1 year ago
JSON representation
Reinforcement Learning for Portfolio Management
- Host: GitHub
- URL: https://github.com/filangelos/qtrader
- Owner: filangelos
- License: apache-2.0
- Archived: true
- Created: 2017-10-07T09:14:33.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-06-26T09:22:29.000Z (almost 8 years ago)
- Last Synced: 2024-08-01T02:11:51.253Z (almost 2 years ago)
- Topics: algorithmic-trading, python, q-learning, recurrent-neural-networks, reinforcement-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 41.6 MB
- Stars: 448
- Watchers: 46
- Forks: 169
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# qtrader
> Reinforcement Learning for Portfolio Management
## Why Reinforcement Learning?
1. Learns the **optimal action**, rather than models the market.
2. Adaptive to temporary changes of the market, due to its online training.
3. Optimizes the long-term (cumulative) reward, rather than the instantaneous benefit.
## Setup
> Exclusively `Python 3` compatible, because of `typing`s
### macOS
* `source scripts/setup.sh`
## Documentation
* [Interim Report](docs/FYP.Interim-Report.pdf): Introduction to `qtrader`
* [Papers Review](docs/FYP.Related-Work.pdf): Motivation, pros & cons of existing methods
* [Resources](docs/FYP.Resources.md): List of relevant resources
* [Final Report](docs/FYP.Final-Report.pdf): Master's Thesis
* [Presentation](docs/FYP.Presentation.pdf): 15 minutes project presentation