Molecule Builder: Environment for Testing Reinforcement Learning Agents

Petr Hyner, Petr Hyner, Jan Hůla, Jan Hůla, Mikoláš Janota

2023

Abstract

We present a reinforcement learning environment designed to test agents’ ability to solve problems that can be naturally decomposed using subgoals. This environment is built on top of the PyVGDL game engine and enables to generate problem instances by specifying the dependency structure of subgoals. Its purpose is to enable faster development of Reinforcement Learning algorithms that solve problems by proposing subgoals and then reaching these subgoals.

Paper Citation

in Harvard Style

Hyner P., Hůla J. and Janota M. (2023). Molecule Builder: Environment for Testing Reinforcement Learning Agents. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA; ISBN 978-989-758-674-3, SciTePress, pages 450-458. DOI: 10.5220/0012257900003595

in Bibtex Style

@conference{ncta23,
author={Petr Hyner and Jan Hůla and Mikoláš Janota},
title={Molecule Builder: Environment for Testing Reinforcement Learning Agents},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA},
year={2023},
pages={450-458},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012257900003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA
TI - Molecule Builder: Environment for Testing Reinforcement Learning Agents
SN - 978-989-758-674-3
AU - Hyner P.
AU - Hůla J.
AU - Janota M.
PY - 2023
SP - 450
EP - 458
DO - 10.5220/0012257900003595
PB - SciTePress