RDDL Repository

The rddlrepository hosts a collection of RDDL (Relational Dynamic Influence Diagram Language) description files. These files cover problems from a wide range of disciplines and include archived problems from previous International Planning Competitions. The repository is integrated with the pyRDDLGym ecosystem, providing a variety of environments for testing and developing planning algorithms. It also includes custom visualizers for a select subset of domains.

Purpose

The rddlrepository hosts a growing collection of RDDL domains and instance files. Its goal is to provide a standard set of benchmark problems for the planning community. rddlrepository includes all previous years’ domains from the probabilistic track of the international planning competition, including other domains submitted by the planning community (Taitler et al., 2023).

Examples

rddlrepository integrates seamless with pyRDDLgym. To load an instance of a specific domain in rddlrepository:

import pyRDDLGym
from rddlrepository.core.manager import RDDLRepoManager

manager = RDDLRepoManager(rebuild=True)
problem_info = manager.get_problem("EarthObservation_ippc2018")

env = pyRDDLGym.make(domain=problem_info.get_domain(), instance=problem_info.get_instance("1"))
env.set_visualizer(problem_info.get_visualizer())

This will compile the RDDL domain and instance description into a standard OpenAI gym environment. If the rddlrepository registers a custom visualizer for a domain, then it will display when the environment is rendered.

References

2023

pyRDDLGym: From RDDL to Gym Environments

Ayal Taitler, Michael Gimelfarb, Jihwan Jeong, Sriram Gopalakrishnan, Martin Mladenov, Xiaotian Liu, and Scott Sanner

In PRL Workshop Series: Bridging the Gap Between AI Planning and Reinforcement Learning, 2023

Bib HTML PDF Code

@inproceedings{taitler2023pyrddlgym,
  title = {pyRDDLGym: From RDDL to Gym Environments},
  author = {Taitler, Ayal and Gimelfarb, Michael and Jeong, Jihwan and Gopalakrishnan, Sriram and Mladenov, Martin and Liu, Xiaotian and Sanner, Scott},
  booktitle = {PRL Workshop Series: Bridging the Gap Between AI Planning and Reinforcement Learning},
  year = {2023},
}