mlsanityData to 14 Oct 2026

PlatoLTL: Scaling LTL-Guided Multi-Task RL

arXiv 2601.22891 ↗First posted 30 Jan 2026cs.LGcited by 2

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Linear temporal logic (LTL) has emerged as a powerful formalism for specifying structured, temporally extended tasks in multi-task reinforcement learning (RL). However, while existing approaches in LTL-guided multi-task RL demonstrate success in simple environments, they suffer from challenges in representation learning and exploration efficiency when applied to high-dimensional environments with parameterized specifications. We present PlatoLTL, which elevates state-of-the-art methods to address both challenges. We model atomic propositions as instances of atomic predicates and inject task parameters directly into the goal embedding to enable efficient generalization. We also leverage simple priors on closeness to predicate satisfaction to enable and accelerate learning of complex tasks without biasing the optimal policy. We validate our approach on challenging environments including robotic manipulation and multi-drone navigation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 51 of its 84 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

51 of 84 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning3 Aug
  2. 2025Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications31 Jan
  3. 2024Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation29 Dec
  4. 2024Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning31 Oct
  5. 2024DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL6 Oct
  6. 2024Directed Exploration in Reinforcement Learning from Linear Temporal Logic18 Aug
  7. 2024Reward Machines for Deep RL in Noisy and Uncertain Environments31 May
  8. 2024LTL-Constrained Policy Optimization with Cycle Experience Replay17 Apr
  9. 2024Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents6 Feb

Other references · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  4. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  8. 2017Deep Setscited by 1,421
  9. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  10. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  11. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  12. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
30 more
  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  2. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 420
  3. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 395
  4. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  5. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 191
  6. 2023LIV: Language-Image Representations and Rewards for Robotic Controlcited by 188
  7. 2023Vision-Language Models as Success Detectorscited by 142
  8. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  9. 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 75
  10. 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 75
  11. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  12. 2018Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definitioncited by 69
  13. 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
  14. 2015Deep Reinforcement Learning in Parameterized Action Spacecited by 68
  15. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  16. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 65
  17. 2021Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logiccited by 39
  18. 2021Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classificationcited by 38
  19. 2019Certified Reinforcement Learning with Logic Guidancecited by 36
  20. 2020Reward Machines for Cooperative Multi-Agent Reinforcement Learningcited by 35
  21. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  22. 2019Modular Deep Reinforcement Learning with Temporal Logic Specificationscited by 25
  23. 2019Unsupervised Grounding of Plannable First-Order Logic Representation from Imagescited by 24
  24. 2023Eventual Discounting Temporal Logic Counterfactual Experience Replaycited by 19
  25. 2021In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specificationscited by 17
  26. 2022Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specificationscited by 12
  27. 2022Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planningcited by 10
  28. 2023Reinforcement Learning of Action and Query Policies with LTL Instructions under Uncertain Event Detectorcited by 5
  29. 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Datacited by 5
  30. 2025Exact Smooth Reformulations for Trajectory Optimization Under Signal Temporal Logic Specificationscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Zero-Shot Instruction Following in RL via Structured LTL Representationscited by 1
  2. 2026Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
  2. 2025Zero-Shot Instruction Following in RL via Structured LTL Representations
  3. 2026Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions
  4. 2024Comp-LTL: Temporal Logic Planning via Zero-Shot Policy Composition
  5. 2024Inductive Generalization in Reinforcement Learning from Specifications
  6. 2026Temporal Logic Guided Universal Task Representations for Reinforcement Learning
  7. 2026SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
  8. 2026Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL