tradinggym
Unverified ML strategy on Crypto by astrologos. BotFinder score 18 out of 100.
A highly-customizable OpenAI gym environment to train & evaluate RL agents trading stocks and crypto.
Source: github
BotFinder analysis pending.
tradinggym
CryptoEnvironment CryptoEnvironment is a gym environment for cryptocurrency trading. It provides a simulation environment for training and evaluating reinforcement learning agents. Features - Supports discrete buying, selling, and holding (optional) actions. - Customizable: - Initial balance - Random initial asset split - Maximum steps - Trade fees - Slippage - Order execution fraction - Reward function - Low entropy action penalty - Uses any trading data including custom indicators from a provided DataFrame. - Provides observation and action spaces compatible with Gym. - Easy integration with stable-baselines3. - Supports one-line evaluation of trained models with visualization and reporting options. Installation Clone the repository: To use the CryptoEnvironment, you need to have the following dependencies installed: - gym==0.21.0 - stable-baselines3==1.8.0 - matplotlib==3.7.1 - numpy - pandas You can install these dependencies using pip: Usage See more detailed examples in /examples/. Here's an example of how to use the CryptoEnvironment: License This project is licensed under the
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)