Sriram Gopalakrishnan, Ph.D.

Sriram Gopalakrishnan, Ph.D.

AI Research Lead at J.P. Morgan Chase | Sequential-Decision Making Problems, Human-AI Interaction, & Generative AI

pyRDDLGym: From RDDL to Gym Environments

Published in ICAPS Workshop on Planning and Reinforcement Learning (PRL 2023), 2023

Recommended citation: Taitler, A., Gimelfarb, M., Jeong, J., Gopalakrishnan, S., Mladenov, M., Liu, X., & Sanner, S. (2023). pyRDDLGym: From RDDL to Gym Environments. In ICAPS PRL Workshop. https://arxiv.org/abs/2211.05939

Abstract

pyRDDLGym automatically parses and executes domain models written in RDDL (Relational Dynamic Influence Diagram Language) into standard Gymnasium simulation environments, enabling seamless interoperability between automated planning solvers and deep reinforcement learning algorithms.

View Publication

Recommended citation: Taitler, A., Gimelfarb, M., Jeong, J., Gopalakrishnan, S., Mladenov, M., Liu, X., & Sanner, S. (2023). pyRDDLGym: From RDDL to Gym Environments. In ICAPS PRL Workshop.