Research paper

MDPax: GPU-accelerated MDP solvers in Python with JAX

Research from Open JournalsPublished by Journal of Open Source Software31 October 2025PDF

Examine a JAX implementation that uses GPUs to solve Markov decision processes in Python.

MDPax: GPU-accelerated MDP solvers in Python with JAX cover

Resource access

Get the full resource

Enter your business details to read the full resource.

First nameLast nameWork emailCompanyJob titleCountry or region

Joseph Farrington, Wai Keong Wong, Kezhi Li, Martin Utley. MDPax: GPU-accelerated MDP solvers in Python with JAX. Journal of Open Source Software. 10.21105/joss.08897. CC BY 4.0. Original PDF, unmodified.

CC BY 4.0

MDPax: GPU-accelerated MDP solvers in Python with JAX

Related research.

TanML: Automated Model Validation Toolkit for Tabular Machine Learning Models

itwinai: A Python Toolkit for Scalable Scientific Machine Learning on HPC Systems

Inference Perf: A Benchmarking Tool for GenAI Inference