# Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2006.08767 · HTML: https://mlsanity.com/paper/2006.08767/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 21 of 21)

- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [The Logical Options Framework](https://mlsanity.com/paper/2102.12571/) (2021)
- [DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL](https://mlsanity.com/paper/2410.04631/) (2024)
- [In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications](https://mlsanity.com/paper/2110.09461/) (2021)
- [Learning to Follow Instructions in Text-Based Games](https://mlsanity.com/paper/2211.04591/) (2022)
- [Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines](https://mlsanity.com/paper/2211.10902/) (2022)
- [One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning](https://mlsanity.com/paper/2508.01561/) (2025)
- [Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines](https://mlsanity.com/paper/2111.09475/) (2021)
- [Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey](https://mlsanity.com/paper/2304.12090/) (2023)
- [Hierarchies of Reward Machines](https://mlsanity.com/paper/2205.15752/) (2022)
- [Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks](https://mlsanity.com/paper/2206.01812/) (2022)
- [Planning with a Learned Policy Basis to Optimally Solve Complex Tasks](https://mlsanity.com/paper/2403.15301/) (2024)
- [Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines](https://mlsanity.com/paper/2403.07005/) (2024)
- [Inductive Generalization in Reinforcement Learning from Specifications](https://mlsanity.com/paper/2406.03651/) (2024)
- [Generalizing LTL Instructions via Future Dependent Options](https://mlsanity.com/paper/2212.04576/) (2022)
- [Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks](https://mlsanity.com/paper/2212.05200/) (2022)
- [Generalization of Compositional Tasks with Logical Specification via Implicit Planning](https://mlsanity.com/paper/2410.09686/) (2024)
- [Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization](https://mlsanity.com/paper/2602.09761/) (2026)
- [Zero-Shot Instruction Following in RL via Structured LTL Representations](https://mlsanity.com/paper/2602.14344/) (2026)
- [Zero-Shot Instruction Following in RL via Structured LTL Representations](https://mlsanity.com/paper/2512.02633/) (2025)
- [Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL](https://mlsanity.com/paper/2609.38065/) (2026)

## Abstract (arXiv)

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular, we present a neuro-symbolic framework where a symbolic module transforms TL specifications into a form that helps the training of a DRL agent targeting generalisation, while a neural module learns systematically to solve the given tasks. We study the emergence of systematic learning in different settings and find that the architecture of the convolutional layers is key when generalising to new instructions. We also provide evidence that systematic learning can emerge with abstract operators such as negation when learning from a few training examples, which previous research have struggled with.