pskrunner14/trading-bot

Stock Trading Bot using Deep Q-Learning

44
/ 100
Emerging

Implements multiple DQN variants (vanilla, fixed target distribution, Double DQN) with a model-free approach that observes n-day price windows, executes buy/sell/hold actions, and updates network parameters via experience replay. Trained on historical Yahoo Finance data, the agent learns optimal trading policies by maximizing portfolio rewards over sequential episodes. Uses CPU-based training due to sequential nature and includes evaluation scripts with portfolio visualization.

1,144 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 25 / 25

How are scores calculated?

Stars

1,144

Forks

357

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/pskrunner14/trading-bot"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.