# Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization

arXiv: https://arxiv.org/abs/2602.09761 · HTML: https://mlsanity.com/paper/2602.09761/

## Key facts

- Cited by 1 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 26 of its 43 references that are in the map.
- First posted on arXiv 10 Feb 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, 26 of 26)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Transfer Learning in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2009.07888/) (2020)
- [Reinforcement learning](https://mlsanity.com/paper/2405.10369/) (2024)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Logic Tensor Networks](https://mlsanity.com/paper/2012.13635/) (2020)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/1706.05064/) (2017)
- [Neural Task Programming: Learning to Generalize Across Hierarchical Tasks](https://mlsanity.com/paper/1710.01813/) (2017)
- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specifications](https://mlsanity.com/paper/1807.06333/) (2018)
- [Environment-Independent Task Specifications via GLTL](https://mlsanity.com/paper/1704.04341/) (2017)
- [Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies](https://mlsanity.com/paper/1807.07665/) (2018)
- [Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas](https://mlsanity.com/paper/2006.01110/) (2020)
- [The Logical Options Framework](https://mlsanity.com/paper/2102.12571/) (2021)
- [Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction](https://mlsanity.com/paper/2010.06797/) (2020)
- [Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning](https://mlsanity.com/paper/2006.08767/) (2020)
- [DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL](https://mlsanity.com/paper/2410.04631/) (2024)
- [Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics](https://mlsanity.com/paper/2204.11833/) (2022)
- [Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines](https://mlsanity.com/paper/2211.10902/) (2022)
- [Neural Reward Machines](https://mlsanity.com/paper/2408.08677/) (2024)
- [Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts](https://mlsanity.com/paper/2510.14538/) (2025)
- [Conformance Checking of Fuzzy Logs against Declarative Temporal Specifications](https://mlsanity.com/paper/2406.12078/) (2024)
- [LTL-Transfer: Skill Transfer for Temporal Task Specification](https://mlsanity.com/paper/2206.05096/) (2022)
- [T-ILR: a Neurosymbolic Integration for LTLf](https://mlsanity.com/paper/2508.15943/) (2025)
- [Fully Learnable Neural Reward Machines](https://mlsanity.com/paper/2509.19017/) (2025)

## Built on by (most cited first, 1 of 1)

- [Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL](https://mlsanity.com/paper/2609.38065/) (2026)

## Abstract (arXiv)

In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed in Linear Temporal Logic in sub-symbolic environments. Previous multi-task work has mostly relied on knowledge of the mapping between raw observations and symbols appearing in the formulae. We drop this unrealistic assumption by jointly training a multi-task policy and a symbol grounder with the same experience. The symbol grounder is trained only from raw observations and sparse rewards via Neural Reward Machines in a semi-supervised fashion. Experiments on vision-based environments show that our method achieves performance comparable to using the true symbol grounding and significantly outperforms the only other previous method for multi-task learning that does not assume knowledge of the true symbol grounding.