Stratifying Reinforcement Learning With Signal Temporal Logic

Abstract

In this paper, we develop a stratification-based semantics for Signal Temporal Logic (STL) in which each atomic predicate is interpreted as a membership test in a stratified space. This perspective reveals a novel correspondence principle between stratification theory and STL, showing that most STL formulas can be viewed as inducing a stratification of space-time. The significance of this interpretation is twofold. First, it offers a fresh theoretical framework for analyzing the structure of the embedding space generated by deep reinforcement learning (DRL) and relates it to the geometry of the ambient decision space. Second, it provides a principled framework that both enables the reuse of existing high-dimensional analysis tools and motivates the creation of novel computational techniques. To ground the theory, we (1) illustrate the role of stratification theory in Minigrid games and (2) apply numerical techniques to the latent embeddings of a DRL agent playing such a game where the

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycurry2026stratifying

Related papers

• Funnel-based Reward Shaping For Signal Temporal Logic Tasks In Reinforcement Learning (2022)7.16
• Stlgame: Signal Temporal Logic Games In Adversarial Multi-agent Systems (2024)0.00
• Deep Reinforcement Learning Based Networked Control With Network Delays For Signal Temporal Logic Specifications (2021)0.00
• Joint Learning Of Policy With Unknown Temporal Constraints For Safe Reinforcement Learning (2023)0.00
• Directed Exploration In Reinforcement Learning From Linear Temporal Logic (2024)0.00
• TGPO: Temporal Grounded Policy Optimization For Signal Temporal Logic Tasks (2025)0.00
• A Hierarchical Reinforcement Learning Method For Persistent Time-sensitive Tasks (2016)0.00
• Learning Probabilistic Temporal Logic Specifications For Stochastic Systems (2025)0.00