mlsanityData to 14 Oct 2026

Tractable Reinforcement Learning for Full Class of Signal Temporal Logic Specifications Using Spatiotemporal Tube Reward

arXiv 2609.28396 ↗First posted 23 Sep 2026cs.RO cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

This paper addresses the control problem for robotic systems, including non-holonomic and underactuated platforms operating under unknown dynamics and strict actuator limits to satisfy complex high-level specifications. We denote these high-level specifications using Signal Temporal Logic (STL) and propose a novel time-aware Reinforcement Learning (RL) framework that leverages the geometric properties of Spatiotemporal Tubes (STTs). While traditional analytical STT controllers often struggle to enforce input constraints, and existing RL approaches rely on memory-intensive state history, our method natively overcomes both limitations. By mapping the logical and temporal complexities of the full class of STL into time-varying geometric boundaries, we directly constrain the multidimensional system state without relying on scalar robustness metrics. Augmenting the state space with time, we train a time-aware Soft Actor-Critic (SAC) agent using a continuous, geometry-aware reward function that eliminates the need to explicitly evaluate complex logical semantics during execution. The proposed framework offers a history-free, computationally efficient approach to learn continuous control policies that ensure robust satisfaction of specifications while strictly adhering to system input constraints.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 19 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

12 of 19 references.

References · 12

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  3. 2020Tractable Reinforcement Learning of Signal Temporal Logic Objectivescited by 22
  4. 2022Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learningcited by 8
  5. 2017Prescribed Performance Control for Signal Temporal Logic Specificationscited by 4
  6. 2022Does DQN Learn?cited by 4
  7. 2024Spatiotemporal Tubes for Temporal Reach-Avoid-Stay Tasks in Unknown Systemscited by 2
  8. 2025Approximation-free Control for Signal Temporal Logic Specifications using Spatiotemporal Tubescited by 2
  9. 2025Prescribed Performance Control of Unknown Euler-Lagrange Systems Under Input Constraintscited by 1
  10. 2025Control Barrier Functions for the Full Class of Signal Temporal Logic Tasks using Spatiotemporal Tubescited by 1
  11. 2025Temporal Reach-Avoid-Stay Control for Differential Drive Systems via Spatiotemporal Tubescited by 1
  12. 2026Learning Spatiotemporal Tubes for Full Class of Signal Temporal Logic Tasks for Control of Unknown Systems under Input Constraintscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints
  2. 2025TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks
  3. 2025Signal Temporal Logic Compliant Co-design of Planning and Control ↗
  4. 2026GraSP-STL: A Graph-Based Framework for Zero-Shot Signal Temporal Logic Planning via Offline Goal-Conditioned Reinforcement Learning
  5. 2026Zero-Shot Signal Temporal Logic Planning with Disjunctive Branch Selection in Dynamic Semantic Maps
  6. 2025Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks
  7. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
  8. 2026Conformal Signal Temporal Logic for Robust Reinforcement Learning Control: A Case Study