Reinforcement-Learning-for-Gold-Trading
Publisher-claimed ML strategy on Multi by JonusNattapong. BotFinder score 51 out of 100.
PPO-based RL system for XAUUSD trading. Trained on 2004-2025 gold price data (15-min intervals).
Source: github
BotFinder analysis pending.
Reinforcement-Learning-for-Gold-Trading
Reinforcement Learning for Gold Trading This repository implements a Reinforcement Learning (RL) system for trading XAUUSD (Gold vs US Dollar) using Proximal Policy Optimization (PPO). The model is trained on historical gold price data from 2004 to 2025, resampled to 15-minute intervals. Features - Custom Trading Environment: Gymnasium-based environment simulating gold trading with realistic constraints - Advanced Features: Log returns, RSI, Moving Averages, Bollinger Bands, MACD, and volume indicators - Risk Management: Position sizing, daily loss limits, profit targets, and drawdown controls - Evaluation Metrics: Sharpe ratio, win rate, max drawdown, and daily profit analysis - Pre-trained Model: Ready-to-use PPO model trained on 1 million timesteps Model Performance (Test Set: 2024-2025) - Average Daily Profit: $51.46 - Win Rate: 69.0% - Max Drawdown: 12.0% - Sharpe Ratio: 7.56 - Average Trades per Day: 2.66 Installation 1. Clone the repository: 2. Create a virtual environment: 3. Install dependencies: Usage Training a New Model To train a new PPO model: Optional arguments: - --cs
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
No drawdown history is stored — only the maximum drawdown reported by the source.
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)