Skip to content

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Notifications You must be signed in to change notification settings

KangOxford/AlphaTrade

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

JAX-LOB

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Architecture of the package:

  • gymnax_exchange: the GPU version of rl_environment
    • jaxob: Jax limit order book
    • jaxen: Jax trading_environment
    • jaxrl: Jax training loop

Dependencies

pip install jax[cuda]==0.4.11 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html jaxlib==0.4.11 -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html distrax brax chex flax optax gymnax wandb  

Installation

To install the latest version of Jaxlob, run:

pip install jaxlob

Citation

If you find this project useful, please cite:

@misc{frey2023jaxlob,
      title={JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading}, 
      author={Sascha Frey and Kang Li and Peer Nagy and Silvia Sapora and Chris Lu and Stefan Zohren and Jakob Foerster and Anisoara Calinescu},
      year={2023},
      eprint={2308.13289},
      archivePrefix={arXiv},
      primaryClass={q-fin.TR}
}

Contribution

About

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •