Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep Reinforcement Learning based Trading Agent for Bitcoin
| Date | Stars |
|---|---|
| 2026-07-24 | 794 |
| 2026-07-25 | 794 |
| 2026-07-28 | 794 |
| 2026-07-30 | 794 |
| 2026-07-31 | 794 |
| 2026-08-05 | 795 |
| 2026-08-06 | 795 |
Today
— stars today
This week
+1 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.13%/day
# Deep Trading Agent [](https://github.com/samre12/deep-trading-agent/blob/master/LICENSE) [](https://www.tensorflow.org/) [](https://www.python.org/download/releases/2.7/) [](https://github.com/samre12/deep-trading-agent/) [](https://github.com/samre12/deep-trading-agent/) [](https://cloud.docker.com/app/samre12/repository/docker/samre12/deep-trading-agent/builds) <br> Deep Reinforcement Learning based Trading Agent for Bitcoin using [DeepSense](https://arxiv.org/abs/1611.01942) Network for Q function approximation. <br><br>  <br> For complete details of the dataset, preprocessing, network architecture and implementation, refer to the [Wiki](https://github.com/samre12/deep-trading-agent/wiki) of this repository. ## Requirements - Python 2.7 - [Tensorflow](https://www.tensorflow.org/) - [Pandas](https://pandas.pydata.org) (for pre-processing Bitcoin Price Series) - [tqdm](https://pypi.python.org/pypi/tqdm) (for displaying progress of training)<br> To setup a ubuntu virtual machine with all the dependencies to run the code, refer to [`assets/vm`](https://github.com/samre12/deep-trading-agent/tree/master/assets/vm). ## Run with Docker Pull the prebuilt docker image directly from docker hub and run it as ```bash docker pull samre12/deep-trading-agent:latest docker run -p 6006:6006 -it samre12/deep-trading-agent:latest ``` **OR**<br> Build the docker image locally by executing the command and the run the image as ```bash docker build -t deep-trading-agent . docker run -p 6006:6006 -it deep-trading-agent ``` This will setup the repository for training the agent and - mount the current directory into `/deep-trading-agent` in the container - during image build, the latest transactions history from the exchange is pulled and sampled to create per-minute scale dataset of Bitcoin prices. This dataset is placed at `/deep-trading-agent/data/btc.csv` - to initiate training of the agent, specify suitable parameters in a config file (an example config file is provided at `/deep-trading-agent/code/config/config.cfg`) and run the code using `/deep-trading-agent/code/main.py` - training supports logging and monitoring through *Tensorboard* - `vim` and `screen` are installed in the container to edit the configuration files and run `tensorboard` - bind port *6006* of container to *6006* of host machine to monitor training using *Tensorboard* ## Support Please give a :star: to this repository to support the project :smile:. ## ToDo ### Docker Support - [X] Add Docker support for a fast and easy start with the project ### Improve Model performance - [X] Extract highest and lowest prices and the volume of Bitcoin traded within a given time interval in the [`Preprocessor`](https://github.com/samre12/deep-trading-agent/blob/f8b5604aac3e68905034e4a0597867f37cecb342/code/process/processor.py#L9) - [X] Use closing, highest, lowest prices and the volume traded as input channels to the model (remove features calculated just using closing prices) - [X] Normalize the price tensors using the price of the previous time step - [X] For the complete state representation, input the remaining number of trades to the model - [X] Use separate diff price blocks to calculate the unrealized PnL - [ ] Use [exponentially decayed weighted unrealized PnL](https://github.com/samre12/deep-trading-agent/wiki/Reward-Function#exponentially-weighted-unrealized-pnl) as a reward function to incorporate current state of investment and stabilize the learning of the agent ## Trading Model is inspired by [
Excerpt of 6,780 characters
Read on GitHub
36
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0e29aec693e4dc08, topic:deep-reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning
matched fp:0e29aec693e4dc08, topic:trading