RL trading environments / backtesting
An event-driven backtesting library built on Backtrader that exposes trading environments as OpenAI Gym environments for deep reinforcement learning experiments.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose for a maintained Gymnasium FX/crypto RL environment with a Backtrader bridge, but it is scoped to specific markets rather than general event-driven backtesting.
Gymnasium trading environment for FX and crypto: backtrader execution bridge, protected SL/TP orders, solvency curricula and audit-grade trade diagnostics
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose if you need MetaTrader 5 RL trading, but it is stale and tied to MT5 rather than a general backtesting library.
A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)
Choose for a lightweight trading RL gym, but it has been unmaintained for years and lacks Backtrader integration.
Trading Gym is an open source project for the development of reinforcement learning algorithms in the context of trading.
Choose for crypto-specific RL trading, but it is unmaintained and not a general backtesting library.
A cryptocurrency trading environment using deep reinforcement learning and OpenAI's gym
Choose for a simple stock-trading Gym environment, but it is stale and lacks Backtrader-based backtesting.
A custom OpenAI gym environment for simulating stock trades on historical price data.
Choose for a generic Gym trading environment, but it is stale and less feature-rich than btGym for RL backtesting.
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Choose for a trading and backtesting RL environment, but it is stale and not as deep-learning-focused as btGym.
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
These projects were analysed and named btgym among their alternatives. The relationship is not symmetric — how btgym rates them is a separate judgement, made when btgym is analysed in its own right.
calls btgym “choose for deep-learning-friendly backtesting, but it's old and unmaintained.”
Python Backtesting library for trading strategies