Specification-Guided Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41032-41033
DOI: 10.1609/aaai.v40i48.42142 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tanmay Ambadkar.
Abstract (Originalsprache)
While Reinforcement Learning (RL) has demonstrated remarkable success in solving complex sequential decision-making problems, its application in real-world, safety-critical systems is hindered by its reliance on carefully engineered reward functions. Designing effective rewards is notoriously challenging and can lead to unintended or unsafe behaviors, a phenomenon known as reward hacking. Specification-guided RL has emerged as a principled alternative, leveraging formal methods to directly encode high-level objectives, safety requirements, and behavioral constraints. However, the practical utility of this approach is often limited by coarse or under-specified logical formulas and the computational challenge of enforcing safety at scale. This thesis addresses these limitations by developing a unified framework for the automated refinement, scalable enforcement, and flexible adaptation of formal specifications in RL.
Zitieren
APA
Ambadkar, T. (2026). Specification-Guided Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41032-41033. https://doi.org/10.1609/aaai.v40i48.42142
Vancouver
Ambadkar T. Specification-Guided Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41032-41033. doi:10.1609/aaai.v40i48.42142
BibTeX
@article{Ambadkar2026,
author = {Ambadkar, Tanmay},
title = {Specification-Guided Reinforcement Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41032--41033},
doi = {10.1609/aaai.v40i48.42142}
}
EUVIMED