Probabilistic Model Checking of Stochastic Reinforcement Learning Policies

Dennis Gross, Helge Spieker

2024

Abstract

We introduce a method to verify stochastic reinforcement learning (RL) policies. This approach is compatible with any RL algorithm as long as the algorithm and its corresponding environment collectively adhere to the Markov property. In this setting, the future state of the environment should depend solely on its current state and the action executed, independent of any previous states or actions. Our method integrates a verification technique, referred to as model checking, with RL, leveraging a Markov decision process, a trained RL policy, and a probabilistic computation tree logic (PCTL) formula to build a formal model that can be subsequently verified via the model checker Storm. We demonstrate our method’s applicability across multiple benchmarks, comparing it to baseline methods called deterministic safety estimates and naive monolithic model checking. Our results show that our method is suited to verify stochastic RL policies.

Paper Citation

in Harvard Style

Gross D. and Spieker H. (2024). Probabilistic Model Checking of Stochastic Reinforcement Learning Policies. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 438-445. DOI: 10.5220/0012357700003636

in Bibtex Style

@conference{icaart24,
author={Dennis Gross and Helge Spieker},
title={Probabilistic Model Checking of Stochastic Reinforcement Learning Policies},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={438-445},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012357700003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Probabilistic Model Checking of Stochastic Reinforcement Learning Policies
SN - 978-989-758-680-4
AU - Gross D.
AU - Spieker H.
PY - 2024
SP - 438
EP - 445
DO - 10.5220/0012357700003636
PB - SciTePress