Home / Backtesting & trading frameworks
hugocen/freqtrade-gym
Gym environment for reinforcement learning in crypto trading
What it is
A customised Gym environment for developing and comparing reinforcement learning algorithms in crypto trading, connected to the freqtrade ecosystem. Market data and trade simulation are wrapped in the standard Gym interface, so different RL algorithms can be trained and compared. Developers and researchers who already know freqtrade and want to try RL methods are the natural audience. Simulated rewards ignore some real trading frictions unless you add them.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Backtesting, Strategy research |
| Markets | Crypto |
| Stack | Python |
| Learning curve | Steep learning curve |
| Practical value | Low practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): −2 over the period, now 229. Gaps mean no snapshot was taken that day.
A customized gym environment for developing and comparing reinforcement learning algorithms in crypto trading.
Similar tools
Record crypto order books and train a DDQN trading agent
High-frequency trading and market-making backtesting in Rust and Python
AI-oriented quantitative investment platform with full ML pipeline
Vectorized Python backtesting and strategy research toolkit
Event-driven backtesting engine for Python trading algorithms
LLM quant tools and market research for US stocks and crypto