Compositional shield synthesis for safe reinforcement learning in partial observability

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Carr, Steven, Bakirtzis, Georgios, Topcu, Ufuk
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909789045391360
author Carr, Steven
Bakirtzis, Georgios
Topcu, Ufuk
author_facet Carr, Steven
Bakirtzis, Georgios
Topcu, Ufuk
contents Agents controlled by the output of reinforcement learning (RL) algorithms often transition to unsafe states, particularly in uncertain and partially observable environments. Partially observable Markov decision processes (POMDPs) provide a natural setting for studying such scenarios with limited sensing. Shields filter undesirable actions to ensure safe RL by preserving safety requirements in the agents' policy. However, synthesizing holistic shields is computationally expensive in complex deployment scenarios. We propose the compositional synthesis of shields by modeling safety requirements by parts, thereby improving scalability. In particular, problem formulations in the form of POMDPs using RL algorithms illustrate that an RL agent equipped with the resulting compositional shielding, beyond being safe, converges to higher values of expected reward. By using subproblem formulations, we preserve and improve the ability of shielded agents to require fewer training episodes than unshielded agents, especially in sparse-reward settings. Concretely, we find that compositional shield synthesis allows an RL agent to remain safe in environments two orders of magnitude larger than other state-of-the-art model-based approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12085
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Compositional shield synthesis for safe reinforcement learning in partial observability
Carr, Steven
Bakirtzis, Georgios
Topcu, Ufuk
Systems and Control
Agents controlled by the output of reinforcement learning (RL) algorithms often transition to unsafe states, particularly in uncertain and partially observable environments. Partially observable Markov decision processes (POMDPs) provide a natural setting for studying such scenarios with limited sensing. Shields filter undesirable actions to ensure safe RL by preserving safety requirements in the agents' policy. However, synthesizing holistic shields is computationally expensive in complex deployment scenarios. We propose the compositional synthesis of shields by modeling safety requirements by parts, thereby improving scalability. In particular, problem formulations in the form of POMDPs using RL algorithms illustrate that an RL agent equipped with the resulting compositional shielding, beyond being safe, converges to higher values of expected reward. By using subproblem formulations, we preserve and improve the ability of shielded agents to require fewer training episodes than unshielded agents, especially in sparse-reward settings. Concretely, we find that compositional shield synthesis allows an RL agent to remain safe in environments two orders of magnitude larger than other state-of-the-art model-based approaches.
title Compositional shield synthesis for safe reinforcement learning in partial observability
topic Systems and Control
url https://arxiv.org/abs/2509.12085