A market environment and benchmark layer for financial reinforcement learning, providing market datasets and trading environments for developing and comparing DRL trading agents.
Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.
FinRL-Meta is the market environment and benchmark component of the FinRL ecosystem. It collects historical market data from many sources and turns it into trading environments that reinforcement learning agents can train and be tested in. Users can compare different agents on the same dataset, which the project positions as a way to make evaluations fairer.
The project covers a data layer that fetches and preprocesses prices and technical indicators from providers such as Alpaca, Binance, Yahoo Finance, Tushare and Baostock, and an environment layer that wraps this data for DRL training. Agents from ElegantRL, Stable-Baselines3 and RLlib can be plugged into the environments directly. It also describes a training, testing and trading pipeline that separates training periods from evaluation periods to reduce information leakage.
FinRL-Meta focuses on the data and environment layers rather than full production deployment. For production-oriented trading infrastructure, the maintainers point to the separate FinRL-X / FinRL-Trading project.
Open the Plug and Play with DRL Agents demo notebook on Colab
Summary generated by AI from the project's README. GitHub stats refresh daily.
A modular Python quant trading framework covering stock selection, portfolio allocation, backtesting and Alpaca broker execution with one weight-based interface.
AI-oriented quantitative investment platform from Microsoft covering data, model training, backtesting and order execution for quant research.
LLM-driven stock analysis system covering A-shares, HK, US, JP, KR and Taiwan stocks, pushing daily decision dashboards to chat apps and email.
An open-source Python framework for applying deep reinforcement learning to automated stock trading and portfolio tasks.
Unity ML-Agents Toolkit lets Unity games and simulations serve as environments for training AI agents with reinforcement and imitation learning.
Python framework for quantitative trading that covers strategy definition, vector and event-driven backtesting, result dashboards, and paper or live trading.