Home / Factor research
TorchTrade/torchtrade
Modular reinforcement learning framework for algorithmic trading
What it is
A modular reinforcement learning framework for algorithmic trading built on PyTorch. Data loading, market environment simulation and agent training are separated into components that can be combined and extended. Researchers and developers who want to explore RL trading models with a clean structure are the intended users. As with other RL trading tools, performance in its simulated environment does not by itself show that a strategy works live.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Developers |
|---|---|
| Used for | Strategy research, Backtesting |
| Markets | Multi-market |
| Stack | Python (PyTorch) |
| Learning curve | Moderate learning curve |
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | GPU optional |
| Maintenance | Last commit 19 days ago |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +5 over the period, now 429. Gaps mean no snapshot was taken that day.
Modular reinforcement learning framework for algorithmic trading
Similar tools
Java library for technical analysis and strategy backtesting
Deep reinforcement learning library for automated quantitative trading
Python algorithmic trading framework with machine learning support
Python backtesting and live trading platform for strategies
Run Pine Script indicators and strategies in JavaScript
Go module for technical indicators, strategies, and backtesting