Making Reinforcement Learning Safer via Curriculum Learning

Kelvin Toonen, Thiago D. Simão

2025

Abstract

The growth of deep reinforcement learning gives rise to safety concerns about applications using reinforcement learning. Therefore, it is crucial to investigate the safety aspect in this field, especially in the domain of robotics where agents can break surrounding objects or themselves. Curriculum learning has the potential to help with creating safer agents, because it helps the agent with learning faster and it allows for the agent to learn in safer and more controlled environments leading up to the target environment. More specifically, we change the environment only slightly to make it easier to transfer knowledge from one environment to the next, while still influencing the exploration process of the agent. This project combines curriculum learning with constrained reinforcement learning, a specific form of incorporating safety, to create a framework that allows agents to learn safely, even during training. This framework is also extended to include automation of the curriculum.

Paper Citation

in Harvard Style

Toonen K. and Simão T. (2025). Making Reinforcement Learning Safer via Curriculum Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 1465-1472. DOI: 10.5220/0013388100003890

in Bibtex Style

@conference{icaart25,
author={Kelvin Toonen and Thiago Simão},
title={Making Reinforcement Learning Safer via Curriculum Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={1465-1472},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013388100003890},
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 - Making Reinforcement Learning Safer via Curriculum Learning
SN - 978-989-758-737-5
AU - Toonen K.
AU - Simão T.
PY - 2025
SP - 1465
EP - 1472
DO - 10.5220/0013388100003890
PB - SciTePress