PDDLGym: Gym environments from PDDL problems

T Silver, R Chitnis - arXiv preprint arXiv:2002.06432, 2020 - arxiv.org
We present PDDLGym, a framework that automatically constructs OpenAI Gym
environments from PDDL domains and problems. Observations and actions in PDDLGym …

Towards Teaching High-Level Behaviors to a Robotic Agent

P Hérail, A Bit-Monnot - HRI Human-Interactive Robot Learning …, 2023 - hal.science
Developing robust autonomous agents require complex execution architectures operating at
several levels of abstraction in order to keep the acting problem tractable. While there is a …