Home / Factor research
hackthemarket/gym-trading
OpenAI Gym environment for reinforcement learning trading
What it is
An environment for training reinforcement learning trading models, built on the OpenAI Gym interface. It provides a simulated market with historical price replay and a reward signal so agents can be trained and evaluated. Researchers and machine learning developers testing RL trading ideas can plug in standard Gym-compatible agents. The simulation is simplified, so behaviour learned here may not transfer to real markets with costs and liquidity limits.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Strategy research, Backtesting |
| Markets | Multi-market |
| Stack | Python |
| Learning curve | Steep learning curve |
| Practical value | Low practical value |
| Cost | Free and open source |
| Hardware | GPU optional |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +1 over the period, now 712. Gaps mean no snapshot was taken that day.
Environment for reinforcement-learning algorithmic trading models
Similar tools
Vectorized Python backtesting and strategy research toolkit
Iterative trading strategy research framework with walk-forward testing
Research framework for RL-enhanced Avellaneda-Stoikov market making
Python library of quantitative finance building blocks
AI-oriented quantitative investment platform with full ML pipeline
Open-source reinforcement learning platform for quantitative trading