# Environment-Independent Task Specifications via GLTL

arXiv: https://arxiv.org/abs/1704.04341 · HTML: https://mlsanity.com/paper/1704.04341/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2017.

## Built on by (most cited first, 30 of 67)

- [LTL2Action: Generalizing LTL Instructions for Multi-Task RL](https://mlsanity.com/paper/2102.06858/) (2021)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [On the Expressivity of Markov Reward](https://mlsanity.com/paper/2111.00876/) (2021)
- [Compositional Reinforcement Learning from Logical Specifications](https://mlsanity.com/paper/2106.13906/) (2021)
- [Deep Reinforcement Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1902.04257/) (2019)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [Multi-Agent Reinforcement Learning with Temporal Logic Specifications](https://mlsanity.com/paper/2102.00582/) (2021)
- [Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs](https://mlsanity.com/paper/2106.00099/) (2021)
- [Cognitive science as a source of forward and inverse models of human decisions for robotics and control](https://mlsanity.com/paper/2109.00127/) (2021)
- [Policy Optimization with Linear Temporal Logic Constraints](https://mlsanity.com/paper/2206.09546/) (2022)
- [On the (In)Tractability of Reinforcement Learning for LTL Objectives](https://mlsanity.com/paper/2111.12679/) (2021)
- [Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees](https://mlsanity.com/paper/2305.01381/) (2023)
- [General agents contain world models](https://mlsanity.com/paper/2506.01622/) (2025)
- [Behavior Alignment via Reward Function Optimization](https://mlsanity.com/paper/2310.19007/) (2023)
- [A First-Occupancy Representation for Reinforcement Learning](https://mlsanity.com/paper/2109.13863/) (2021)
- [Policy Synthesis and Reinforcement Learning for Discounted LTL](https://mlsanity.com/paper/2305.17115/) (2023)
- [Goals as Reward-Producing Programs](https://mlsanity.com/paper/2405.13242/) (2024)
- [Three Dogmas of Reinforcement Learning](https://mlsanity.com/paper/2407.10583/) (2024)
- [Verifiable and Compositional Reinforcement Learning Systems](https://mlsanity.com/paper/2106.05864/) (2021)
- [Computably Continuous Reinforcement-Learning Objectives are PAC-learnable](https://mlsanity.com/paper/2303.05518/) (2023)
- [A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs](https://mlsanity.com/paper/2310.12248/) (2023)
- [Learning to Follow Instructions in Text-Based Games](https://mlsanity.com/paper/2211.04591/) (2022)
- [Embedding Symbolic Temporal Knowledge into Deep Sequential Models](https://mlsanity.com/paper/2101.11981/) (2021)
- [Reward Machines for Deep RL in Noisy and Uncertain Environments](https://mlsanity.com/paper/2406.00120/) (2024)
- [Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines](https://mlsanity.com/paper/2211.10902/) (2022)
- [Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning](https://mlsanity.com/paper/2205.12532/) (2022)
- [Specification-Guided Learning of Nash Equilibria with High Social Welfare](https://mlsanity.com/paper/2206.03348/) (2022)
- [Learning Task Automata for Reinforcement Learning using Hidden Markov Models](https://mlsanity.com/paper/2208.11838/) (2022)
- [Neural Reward Machines](https://mlsanity.com/paper/2408.08677/) (2024)
- [Exploiting Contextual Structure to Generate Useful Auxiliary Tasks](https://mlsanity.com/paper/2303.05038/) (2023)

## Abstract (arXiv)

We propose a new task-specification language for Markov decision processes that is designed to be an improvement over reward functions by being environment independent. The language is a variant of Linear Temporal Logic (LTL) that is extended to probabilistic specifications in a way that permits approximations to be learned in finite time. We provide several small environments that demonstrate the advantages of our geometric LTL (GLTL) language and illustrate how it can be used to specify standard reinforcement-learning tasks straightforwardly.