# Temporal Logic Guided Universal Task Representations for Reinforcement Learning

arXiv: https://arxiv.org/abs/2608.15509 · HTML: https://mlsanity.com/paper/2608.15509/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12514/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023)
- [Scalable methods for computing state similarity in deterministic Markov Decision Processes](https://mlsanity.com/paper/1911.09291/) (2019)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)
- [Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks](https://mlsanity.com/paper/2110.03655/) (2021)
- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects](https://mlsanity.com/paper/2305.05706/) (2023)
- [AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond](https://mlsanity.com/paper/2311.16468/) (2023)
- [Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic](https://mlsanity.com/paper/2102.12855/) (2021)
- [Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas](https://mlsanity.com/paper/2006.01110/) (2020)
- [MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation](https://mlsanity.com/paper/2503.13446/) (2025)
- [DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL](https://mlsanity.com/paper/2410.04631/) (2024)
- [NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments](https://mlsanity.com/paper/2402.06838/) (2024)
- [Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2411.00205/) (2024)
- [Unsupervised Representation Learning in Deep Reinforcement Learning: A Review](https://mlsanity.com/paper/2208.14226/) (2022)
- [Learning to Follow Instructions in Text-Based Games](https://mlsanity.com/paper/2211.04591/) (2022)
- [Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning](https://mlsanity.com/paper/2209.13220/) (2022)
- [Learning Multi-Task Transferable Rewards via Variational Inverse Reinforcement Learning](https://mlsanity.com/paper/2206.09498/) (2022)
- [Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation](https://mlsanity.com/paper/2412.20338/) (2024)

## Abstract (arXiv)

Task guided agents demonstrate strong performance in a wide range of complex tasks. However, most existing task representation algorithms are tailored to specific contexts and struggle to generalize across diverse scenarios. Moreover, they typically depend on gradient signals from reinforcement learning controllers to update their weights, which can degrade both representation quality and learning efficiency. To overcome these limitations, we propose LOTUS, a temporal logic inspired universal task representation framework that can be seamlessly integrated into any RL algorithm to enhance agent performance across diverse task settings. Specifically, we design a novel task representation architecture capable of modeling relationships and extracting task semantics from LTL formulas. We further introduce a more effective update mechanism that treats the LTL encoder as a policy, thereby improving representation capacity. To enhance stability and robustness, LOTUS leverages the bisimulation metric, which provides theoretical guarantees for LTL representation, including behavioral equivalence, optimality fidelity, and trajectory robustness. Experimental results show that LOTUS outperforms most existing methods in learning efficiency, generalization capability, and representation quality. Specifically, LOTUS accelerates convergence over 20% in single-task scenarios, achieves a 15%-45% higher success rate in unseen manipulation tasks, and improves generalization performance over 25% in complex multi-task environments with increased sub-goal depth or conjunctions. The corresponding code, videos, and appendix are available at: https://lotus-website.github.io/.