mlsanityData to 14 Oct 2026

Environment-Independent Task Specifications via GLTL

arXiv 1704.04341 ↗First posted 14 Apr 2017cs.AIcited by 67

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 15; 2022: 11; 2023: 15; 2024: 12; 2025: 5; 2026: 8.

67 papers.

Sort:

By area:

  1. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  2. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  3. 2021On the Expressivity of Markov Rewardcited by 71
  4. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  5. 2019Deep Reinforcement Learning from Policy-Dependent Human Feedbackcited by 56
  6. 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environmentscited by 53
  7. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  8. 2021Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPscited by 22
  9. 2021Cognitive science as a source of forward and inverse models of human decisions for robotics and controlcited by 22
  10. 2022Policy Optimization with Linear Temporal Logic Constraintscited by 19
  11. 2021On the (In)Tractability of Reinforcement Learning for LTL Objectivescited by 18
  12. 2023Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guaranteescited by 18
38 more
  1. 2025General agents contain world modelscited by 17
  2. 2023Behavior Alignment via Reward Function Optimizationcited by 16
  3. 2021A First-Occupancy Representation for Reinforcement Learningcited by 14
  4. 2023Policy Synthesis and Reinforcement Learning for Discounted LTLcited by 14
  5. 2024Goals as Reward-Producing Programscited by 14
  6. 2024Three Dogmas of Reinforcement Learningcited by 14
  7. 2021Verifiable and Compositional Reinforcement Learning Systemscited by 13
  8. 2023Computably Continuous Reinforcement-Learning Objectives are PAC-learnablecited by 13
  9. 2023A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPscited by 13
  10. 2022Learning to Follow Instructions in Text-Based Gamescited by 12
  11. 2021Embedding Symbolic Temporal Knowledge into Deep Sequential Modelscited by 11
  12. 2024Reward Machines for Deep RL in Noisy and Uncertain Environmentscited by 11
  13. 2022Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machinescited by 10
  14. 2022Skill Machines: Temporal Logic Skill Composition in Reinforcement Learningcited by 9
  15. 2022Specification-Guided Learning of Nash Equilibria with High Social Welfarecited by 8
  16. 2022Learning Task Automata for Reinforcement Learning using Hidden Markov Modelscited by 7
  17. 2024Neural Reward Machinescited by 7
  18. 2023Exploiting Contextual Structure to Generate Useful Auxiliary Taskscited by 6
  19. 2023Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structurecited by 6
  20. 2021Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operatorcited by 5
  21. 2022Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checkingcited by 5
  22. 2023Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Surveycited by 5
  23. 2024Probabilistic Model Checking of Stochastic Reinforcement Learning Policiescited by 5
  24. 2022RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agentscited by 4
  25. 2023Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behaviorcited by 4
  26. 2024Goal Inference from Open-Ended Dialogcited by 4
  27. 2023Verifiable Reinforcement Learning Systems via Compositionalitycited by 3
  28. 2024On the Uniqueness of Solution for the Bellman Equation of LTL Objectivescited by 3
  29. 2024Inductive Generalization in Reinforcement Learning from Specificationscited by 3
  30. 2025Turn-based Multi-Agent Reinforcement Learning Model Checkingcited by 3
  31. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  32. 2021Task-Guided Inverse Reinforcement Learning Under Partial Informationcited by 2
  33. 2023Reinforcement Learning with Depreciating Assetscited by 2
  34. 2024L^*LM: Learning Automata from Examples using Natural Language Oraclescited by 2
  35. 2021Supervised Bayesian Specification Inference from Demonstrationscited by 1
  36. 2021Regular Decision Processes for Grid Worldscited by 1
  37. 2022Task-Guided IRL in POMDPs that Scalescited by 1
  38. 2023Reward-Machine-Guided, Self-Paced Reinforcement Learningcited by 1

50 most cited of 67 All 67 (JSON)