× pyRDDLGym version 2.x is now official! For those preferring, version 1.4.4 remains accessible through both GitHub and pip installation.
Menu

Welcome to pyRDDLGym.

A Python toolkit for auto-generation of OpenAI Gym environments from Relational Dynamic Influence Diagram Language (RDDL) description files
Learn More
-->
about

What is pyRDDLGym?

pyRDDLGym is the official generator of Gym environments from RDDL files.

pyRDDLGym supports the simulation of general Markov Decision Processes (MDPs) described in the Relational Dynamic Influence Diagram Language (RDDL). Notably, it allows for the modeling of complex environments with concurrent events, indigenous and exogenous noises in a lifted (object-oriented specification) way, enabling automatic scaling of environments from a single object to thousands without changing the model. It is significantly faster and easier than coding environments directly using programming languages. pyRDDLGym allows for rapid development of environments, verification of environments, and easy transfer and sharing since there is no code involved. Additionally, pyRDDLGym contains built-in examples ranging from classical control and operations research to complex networked traffic signal control.

pyRDDLGym eliminates the need for coding, transitioning seamlessly from problem design to simulation instantaneously.

Features

Great features you'll love.

Efficient

Rapid development involves defining an environment in a few lines of RDDL code instead of hundreds of lines of Python code.

Scalable

Automatic scaling up of the environment is achieved by simply setting the number of objects to simulate, without the need for reprogramming the environment.

Additional Tools

pyRDDLGym comes with additional tools, e.g., DBNs generator, Symbolic Representations, and built-in planners such as JaxPlan and PROST.

Python Interface

A fully Python package, 100% compatible with OpenAI Gym. You can seamlessly use your favorite Gym-interacting agent with pyRDDLGym environments.

Reproducible

All simulations from pyRDDLGym are reproducible, making it easy to debug and improve reinforcement learning and planning algorithms.

Open Source

pyRDDLGym is an open source project under MIT license. Welcome to feedback your issues and suggestions.

Get started now.

Pip install the package, or download the source code.