#9898th of 105 in ML frameworks and librariesFor finance and business, trading, stocks and crypto, finance and accounting
tensortrade
Python framework for training reinforcement learning agents on trading environments
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7.2k
- License
- Apache-2.0
- Last commit
- Feb 2026
- Last release
- Feb 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
TensorTrade provides composable pieces for RL trading: environments, action schemes (default Buy/Sell/Hold), reward schemes (default Position-Based Returns), observers, data feeds, and a simulated exchange with configurable commission. Training scripts use Ray RLlib and Optuna. The README reports PPO agents on BTC/USD beating buy-and-hold at 0% commission but losing at 0.1%.
Who it is for: Researchers and quants experimenting with RL for algorithmic trading in Python
Strengths
- Swappable action, reward, observer and exchange components with documented defaults
- Example scripts for Ray RLlib training and Optuna hyperparameter search
- Tutorial curriculum plus a published experiments log with negative results
- Simulated exchange has configurable commission for testing cost sensitivity
Weaknesses
- README results show the agent losing to buy-and-hold at 0.1% commission
- Python version stated inconsistently: 3.12+ in badge and quick start, 3.11 or 3.12 in install
- Simulation only; README describes no live trading or broker integration
- Install pins and TensorFlow/NumPy conflicts are listed in troubleshooting
What it needs
- GPU optional
- Docker
- Needs Ray RLlib, Optuna, TensorFlow, Jupyter
- Models: PPO
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |