TradingGym is a toolkit (in Python) for creating trading and backtesting environments, especially for reinforcement learning agents, but also for simpler rule-based algorithms. It follows a design inspired by OpenAI Gym, offering various environments, data formats (tick data and OHLC), and tools to simulate trading with costs, position limits, observation windows etc. Licensed under MIT. This training environment was originally designed for tickdata, but also supports OHLC data format. WIP. The list contains the feature columns to use in the trading status.
Features
- Environments for RL training, with “step”, “reset”, “render”, etc., following Gym-style API
- Support for both tick data and OHLC data input formats for observations
- Fee/cost modeling, max position constraints, features for bid/ask pricing etc.
- Ability to inspect transaction details, reward, state, etc., for debugging/training
- Simple installation via python setup.py install and integration with standard data tools (pandas, numpy)
- Visualization/rendering support to see how trades/actions evolve over steps/environment episodes
Project Samples
Categories
Algorithmic TradingLicense
MIT LicenseFollow TradingGym
You Might Also Like
Gen AI apps are built with MongoDB Atlas
MongoDB Atlas provides built-in vector search and a flexible document model so developers can build, scale, and run gen AI apps without stitching together multiple databases. From LLM integration to semantic search, Atlas simplifies your AI architecture—and it’s free to get started.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of TradingGym!