mlsanityData to 14 Oct 2026

Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey

arXiv 2304.12090 ↗First posted 24 Apr 2023cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Reinforcement Learning (RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well as safety and interpretability concerns. The core reason underlying such dilemmas can be attributed to the fact that most of the work has focused on the computational aspect of value functions or policies using a representational model to describe atomic components of rewards, states and actions etc, thus neglecting the rich high-level declarative domain knowledge of facts, relations and rules that can be either provided a priori or acquired through reasoning over time. Recently, there has been a rapidly growing interest in the use of Knowledge Representation and Reasoning (KRR) methods, usually using logical languages, to enable more abstract representation and efficient learning in RL. In this survey, we provide a preliminary overview on these endeavors that leverage the strengths of KRR to help solving various problems in RL, and discuss the challenging open problems and possible directions for future work in this area.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 74 of its 169 references that are in the map. First posted on arXiv 24 Apr 2023.

Builds on

74 of 169 references.

References · 74

  1. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  2. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  3. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  4. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  5. 2017Safe Reinforcement Learning via Shieldingcited by 449
  6. 2017Deep Reinforcement Learning: An Overviewcited by 333
  7. 2019Reinforcement Learning in Healthcare: A Surveycited by 310
  8. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
  9. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  10. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 191
  11. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  12. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
38 more
  1. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
  2. 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
  3. 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 75
  4. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  5. 2018Relational Deep Reinforcement Learningcited by 73
  6. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  7. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  8. 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
  9. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  10. 2017Environment-Independent Task Specifications via GLTLcited by 67
  11. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  12. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 61
  13. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  14. 2019Joint Inference of Reward Machines and Policies for Reinforcement Learningcited by 56
  15. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  16. 2019Neural Logic Reinforcement Learningcited by 53
  17. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 52
  18. 2018Logically-Constrained Reinforcement Learningcited by 51
  19. 2020Neurosymbolic Reinforcement Learning with Formally Verified Explorationcited by 49
  20. 2017Interpretable Policies for Reinforcement Learning by Genetic Programmingcited by 48
  21. 2020A Boolean Task Algebra for Reinforcement Learningcited by 48
  22. 2020Cautious Reinforcement Learning with Logical Constraintscited by 45
  23. 2021Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learningcited by 45
  24. 2019Certified Reinforcement Learning with Logic Guidancecited by 36
  25. 2020Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulascited by 36
  26. 2020Reward Machines for Cooperative Multi-Agent Reinforcement Learningcited by 35
  27. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 34
  28. 2015Safety-Constrained Reinforcement Learning for MDPscited by 33
  29. 2019Transfer of Temporal Logic Formulas in Reinforcement Learningcited by 31
  30. 2020Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Taskscited by 28
  31. 2021Multi-Agent Reinforcement Learning with Temporal Logic Specificationscited by 27
  32. 2019Modular Deep Reinforcement Learning with Temporal Logic Specificationscited by 25
  33. 2020Safe Reinforcement Learning with Natural Language Constraintscited by 23
  34. 2022Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversitycited by 22
  35. 2020Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learningcited by 21
  36. 2022Planning for Sample Efficient Imitation Learningcited by 20
  37. 2023Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programscited by 20
  38. 2022Policy Optimization with Linear Temporal Logic Constraintscited by 19

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 2.

5 papers.

  1. 2023Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approachcited by 7
  2. 2023Symbolic Imitation Learning: From Black-Box to Explainable Driving Policiescited by 1
  3. 2024Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtaskscited by 0
  4. 2025SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learningcited by 0
  5. 2025Learning with Expert Abstractions for Efficient Multi-Task Continuous Controlcited by 0