deep-rl-trading
Unverified ML strategy on Multi by mattjhawken. BotFinder score 18 out of 100.
A transformer-based deep RL trading bot built with PyTorch.
Source: github
BotFinder analysis pending.
deep-rl-trading
A Deep-RL Transformer-Based Trading Agent in PyTorch This repository contains a trading agent that leverages deep-Q learning (RL) and an encoder-based transformer, built in PyTorch. Quickstart Guide Requirements - Python 3.9 or later Clone the repository: Set up a virtual environment (optional but recommended): Install dependencies: Running the Agent To run the agent and start training, use the following command: Key Input Parameters The agent's behavior is controlled by several key parameters, detailed below: Machine Learning Parameters - embeddings: The size of the embedding layer in the transformer model. - layers: The number of transformer layers used in the model. - heads: The number of attention heads in each transformer layer. - fwex: Forward expansion size of the transformer's feed-forward network. - dropout: Dropout rate used in the transformer model to prevent overfitting. - neurons: The number of neurons in the fully connected layers of the network. - lr (Learning Rate): Controls how much to change the model in response to the estimated error each time the model weights ar
⚠ 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)