mlsanityData to 14 Oct 2026

Inductive Generalization in Reinforcement Learning from Specifications

arXiv 2406.03651 ↗First posted 5 Jun 2024cs.LG cs.AI cs.LOcited by 3

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

We present a novel inductive generalization framework for RL from logical specifications. Many interesting tasks in RL environments have a natural inductive structure. These inductive tasks have similar overarching goals but they differ inductively in low-level predicates and distributions. We present a generalization procedure that leverages this inductive relationship to learn a higher-order function, a policy generator, that generates appropriately adapted policies for instances of an inductive task in a zero-shot manner. An evaluation of the proposed approach on a set of challenging control benchmarks demonstrates the promise of our framework in generalizing to unseen policies for long-horizon tasks.

Key facts. Cited by 3 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 33 of its 45 references that are in the map. First posted on arXiv 5 Jun 2024.

Builds on

33 of 45 references.

References · 33

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2016Concrete Problems in AI Safetycited by 1,642
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  6. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  7. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  8. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  9. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  10. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  11. 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 98
  12. 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
21 more
  1. 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 75
  2. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  3. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  4. 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
  5. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  6. 2017Environment-Independent Task Specifications via GLTLcited by 67
  7. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  8. 2018Logically-Constrained Reinforcement Learningcited by 51
  9. 2018Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependenciescited by 43
  10. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  11. 2020Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulascited by 36
  12. 2019Transfer of Temporal Logic Formulas in Reinforcement Learningcited by 31
  13. 2020Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Taskscited by 28
  14. 2019Modular Deep Reinforcement Learning with Temporal Logic Specificationscited by 25
  15. 2020Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learningcited by 21
  16. 2023Explore to Generalize in Zero-Shot RLcited by 20
  17. 2022GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesiscited by 16
  18. 2021Neurosymbolic Transformers for Multi-Agent Communicationcited by 13
  19. 2022Specification-Guided Learning of Nash Equilibria with High Social Welfarecited by 8
  20. 2023Robust Subtask Learning for Compositional Generalizationcited by 4
  21. 2022Generalizing LTL Instructions via Future Dependent Optionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specificationscited by 0
  2. 2026Certificate-Guided Evaluation of Reinforcement Learning Generalizationcited by 0
  3. 2026Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RLcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning
  2. 2026PlatoLTL: Scaling LTL-Guided Multi-Task RL
  3. 2026SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
  4. 2026Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
  5. 2024Generalization of Compositional Tasks with Logical Specification via Implicit Planning
  6. 2025Rule-Guided Reinforcement Learning Policy Evaluation and Improvement
  7. 2024LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition
  8. 2024DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL