Environment Descriptions for Usability and Generalisation in Reinforcement Learning

Dennis J. N. J. Soemers, Spyridon Samothrakis, Kurt Driessens, Mark H. M. Winands

2025

Abstract

The majority of current reinforcement learning (RL) research involves training and deploying agents in environments that are implemented by engineers in general-purpose programming languages and more advanced frameworks such as CUDA or JAX. This makes the application of RL to novel problems of interest inaccessible to small organisations or private individuals with insufficient engineering expertise. This position paper argues that, to enable more widespread adoption of RL, it is important for the research community to shift focus towards methodologies where environments are described in user-friendly domain-specific or natural languages. Aside from improving the usability of RL, such language-based environment descriptions may also provide valuable context and boost the ability of trained agents to generalise to unseen environments within the set of all environments that can be described in any language of choice.

Paper Citation

in Harvard Style

Soemers D., Samothrakis S., Driessens K. and Winands M. (2025). Environment Descriptions for Usability and Generalisation in Reinforcement Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 983-992. DOI: 10.5220/0013247300003890

in Bibtex Style

@conference{icaart25,
author={Dennis Soemers and Spyridon Samothrakis and Kurt Driessens and Mark Winands},
title={Environment Descriptions for Usability and Generalisation in Reinforcement Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={983-992},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013247300003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Environment Descriptions for Usability and Generalisation in Reinforcement Learning
SN - 978-989-758-737-5
AU - Soemers D.
AU - Samothrakis S.
AU - Driessens K.
AU - Winands M.
PY - 2025
SP - 983
EP - 992
DO - 10.5220/0013247300003890
PB - SciTePress