Zero-Shot Instruction Following in RL via Structured LTL Representations

• URL: http://arxiv.org/abs/2512.02633v1
• Date: Tue, 02 Dec 2025 10:44:51 GMT
• Title: Zero-Shot Instruction Following in RL via Structured LTL Representations
• Authors: Mattia Giuri, Mathias Jackermeier, Alessandro Abate,
• Abstract summary: Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents.<n>Recent work has shown that interpreting instructions as finite automata, which can be seen as high-level programs monitoring task progress, enables learning a single generalist policy capable of executing arbitrary instructions at test time.<n>We propose a novel approach to learning a multi-task policy for following arbitrary instructions that addresses this shortcoming.
• Score: 54.08661695738909
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents. Recent work has shown that interpreting LTL instructions as finite automata, which can be seen as high-level programs monitoring task progress, enables learning a single generalist policy capable of executing arbitrary instructions at test time. However, existing approaches fall short in environments where multiple high-level events (i.e., atomic propositions) can be true at the same time and potentially interact in complicated ways. In this work, we propose a novel approach to learning a multi-task policy for following arbitrary LTL instructions that addresses this shortcoming. Our method conditions the policy on sequences of simple Boolean formulae, which directly align with transitions in the automaton, and are encoded via a graph neural network (GNN) to yield structured task representations. Experiments in a complex chess-based environment demonstrate the advantages of our approach.

Related papers

• Zero-Shot Instruction Following in RL via Structured LTL Representations [50.41415009303967]
  We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.<n>In this setting, linear temporal logic has recently been adopted as a powerful framework for specifying structured, temporally extended tasks.<n>While existing approaches successfully train generalist policies, they often struggle to effectively capture the rich logical and temporal structure inherent in specifications.
  arXiv  Detail & Related papers  (2026-02-15T23:22:50Z)
• Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions [61.479946958462754]
  We study multi-task reinforcement learning (RL), a setting in which an agent learns a single, universal policy.<n>We present a novel task embedding technique leveraging a new generation of semantic translations-to-automata.
  arXiv  Detail & Related papers  (2026-02-06T14:46:27Z)
• PlatoLTL: Learning to Generalize Across Symbols in LTL Instructions for Multi-Task RL [55.58188508467081]
  linear temporal logic (LTL) is a powerful formalism for specifying structured, temporally extended tasks to RL agents.<n>We present PlatoLTL, a novel approach that enables policies to zero-shot generalize not only compositionally across formula structures, but also parametrically across propositions.
  arXiv  Detail & Related papers  (2026-01-30T12:11:55Z)
• Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards [49.7719149179179]
  This paper investigates the feasibility of using PPO for reinforcement learning (RL) from explicitly programmed reward signals. We focus on tasks expressed through formal languages, such as programming, where explicit reward functions can be programmed to automatically assess quality of generated outputs. Our results show that pure RL-based training for the two formal language tasks is challenging, with success being limited even for the simple arithmetic task.
  arXiv  Detail & Related papers  (2024-10-22T15:59:58Z)
• DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL [59.01527054553122]
  Linear temporal logic (LTL) has recently been adopted as a powerful formalism for specifying complex, temporally extended tasks.<n>Existing approaches suffer from several shortcomings.<n>We propose a novel learning approach to address these concerns.
  arXiv  Detail & Related papers  (2024-10-06T21:30:38Z)
• Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents [9.529492371336286]
  Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. We propose a novel approach, called Logical Specifications-guided Dynamic Task Sampling (LSTS) LSTS learns a set of RL policies to guide an agent from an initial state to a goal state based on a high-level task specification.
  arXiv  Detail & Related papers  (2024-02-06T04:00:21Z)
• Large Language Models as General Pattern Machines [64.75501424160748]
  We show that pre-trained large language models (LLMs) are capable of autoregressively completing complex token sequences. Surprisingly, pattern completion proficiency can be partially retained even when the sequences are expressed using tokens randomly sampled from the vocabulary. In this work, we investigate how these zero-shot capabilities may be applied to problems in robotics.
  arXiv  Detail & Related papers  (2023-07-10T17:32:13Z)
• Procedures as Programs: Hierarchical Control of Situated Agents through Natural Language [81.73820295186727]
  We propose a formalism of procedures as programs, a powerful yet intuitive method of representing hierarchical procedural knowledge for agent command and control. We instantiate this framework on the IQA and ALFRED datasets for NL instruction following.
  arXiv  Detail & Related papers  (2021-09-16T20:36:21Z)
• LTL2Action: Generalizing LTL Instructions for Multi-Task RL [4.245018630914216]
  We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. We employ a well-known formal language -- linear temporal logic (LTL) -- to specify instructions, using a domain-specific vocabulary.
  arXiv  Detail & Related papers  (2021-02-13T04:05:46Z)
• Certified Reinforcement Learning with Logic Guidance [78.2286146954051]
  We propose a model-free RL algorithm that enables the use of Linear Temporal Logic (LTL) to formulate a goal for unknown continuous-state/action Markov Decision Processes (MDPs) The algorithm is guaranteed to synthesise a control policy whose traces satisfy the specification with maximal probability.
  arXiv  Detail & Related papers  (2019-02-02T20:09:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.