mlsanityData to 7 Oct 2026

GraSP-STL: A Graph-Based Framework for Zero-Shot Signal Temporal Logic Planning via Offline Goal-Conditioned Reinforcement Learning

arXiv 2603.29533 ↗First posted 31 Mar 2026cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

Abstract (arXiv)

This paper studies offline, zero-shot planning under Signal Temporal Logic (STL) specifications. We assume access only to an offline dataset of state-action-state transitions collected by a task-agnostic behavior policy, with no analytical dynamics model, no further environment interaction, and no task-specific retraining. The objective is to synthesize a control strategy whose resulting trajectory satisfies an arbitrary unseen STL specification. To this end, we propose GraSP-STL, a graph-search-based framework for zero-shot STL planning from offline trajectories. The method learns a goal-conditioned value function from offline data and uses it to induce a finite-horizon reachability metric over the state space. Based on this metric, it constructs a directed graph abstraction whose nodes represent representative states and whose edges encode feasible short-horizon transitions. Planning is then formulated as a graph search over waypoint sequences, evaluated using arithmetic-geometric mean robustness and its interval semantics, and executed by a learned goal-conditioned policy. The proposed framework separates reusable reachability learning from task-conditioned planning, enabling zero-shot generalization to unseen STL tasks and long-horizon planning through the composition of short-horizon behaviors from offline data. Experimental results demonstrate its effectiveness on a range of offline STL planning tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 16 of its 24 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

16 of 24 references.

References · 16

  1. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  2. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 133
  3. 2020Tractable Reinforcement Learning of Signal Temporal Logic Objectivescited by 21
  4. 2022Multi-agent Motion Planning from Signal Temporal Logic Specificationscited by 21
  5. 2019Arithmetic-Geometric Mean Robustness for Control from Signal Temporal Logic Specificationscited by 19
  6. 2022Mixed-Integer Programming for Signal Temporal Logic with Fewer Binary Variablescited by 15
  7. 2023Signal Temporal Logic Neural Predictive Controlcited by 12
  8. 2024Formal Synthesis of Controllers for Safety-Critical Autonomous Systems: Developments and Challengescited by 12
  9. 2025Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learningcited by 12
  10. 2025Test-Time Graph Search for Goal-Conditioned Reinforcement Learningcited by 8
  11. 2021STL2vec: Signal Temporal Logic Embeddings for Control Synthesis With Recurrent Neural Networkscited by 7
  12. 2024Robust-Locomotion-by-Logic: Perturbation-Resilient Bipedal Locomotion via Signal Temporal Logic Guided Model Predictive Controlcited by 7
4 more
  1. 2023Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specificationscited by 6
  2. 2025Zero-Shot Trajectory Planning for Signal Temporal Logic Taskscited by 6
  3. 2022Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learningcited by 4
  4. 2026RRTη: Sampling-based Motion Planning and Control from STL Specifications using Arithmetic-Geometric Mean Robustnesscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications ↗
  2. 2025TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
  3. 2022Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning
  4. 2024Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning
  5. 2025Zero-Shot Instruction Following in RL via Structured LTL Representations
  6. 2026Shortcut Trajectory Planning for Efficient Offline Reinforcement Learning
  7. 2026Zero-Shot Instruction Following in RL via Structured LTL Representations
  8. 2026Temporal Logic Guidance for Action-Only Diffusion Policies with World Models