mlsanityData to 13 Oct 2026

A Survey of Reinforcement Learning Informed by Natural Language

arXiv 1906.03926 ↗First posted 10 Jun 2019cs.LG cs.AI cs.CLcited by 154

Not on the map. Why?

Abstract (arXiv)

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.

Key facts. Cited by 154 papers in the map (data through 13 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2019: 1; 2020: 4; 2021: 30; 2022: 38; 2023: 33; 2024: 19; 2025: 19; 2026: 10.

154 papers.

Sort:

By area:

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,321
  2. 2019Fine-Tuning Language Models from Human Preferencescited by 2,139
  3. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,219
  4. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 751
  5. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 739
  6. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 339
  7. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 290
  8. 2022Interactive Language: Talking to Robots in Real Timecited by 218
  9. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 209
  10. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 194
  11. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 186
  12. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
38 more
  1. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 164
  2. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 148
  3. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 144
  4. 2023Large Language Models for Robotics: A Surveycited by 132
  5. 2023Training Language Models with Language Feedback at Scalecited by 126
  6. 2024Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizingcited by 125
  7. 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 118
  8. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  9. 2024Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methodscited by 114
  10. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
  11. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  12. 2024HiRT: Enhancing Robotic Control with Hierarchical Robot Transformerscited by 74
  13. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 72
  14. 2023Learning to Model the World with Languagecited by 68
  15. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  16. 2023"No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomycited by 60
  17. 2022Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Modelscited by 58
  18. 2022Improving Intrinsic Exploration with Language Abstractionscited by 49
  19. 2022Training Language Models with Language Feedbackcited by 49
  20. 2021Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learningcited by 45
  21. 2023Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manualscited by 45
  22. 2023LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programscited by 45
  23. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  24. 2021ELLA: Exploration through Learned Language Abstractioncited by 42
  25. 2020Learning Rewards from Linguistic Feedbackcited by 41
  26. 2021Tell me why! Explanations support learning relational and causal structurecited by 36
  27. 2023Learning adaptive planning representations with natural language guidancecited by 36
  28. 2021Deep reinforcement learning in medical imaging: A literature reviewcited by 34
  29. 2021Survey on reinforcement learning for language processingcited by 31
  30. 2021Core Challenges in Embodied Vision-Language Planningcited by 30
  31. 2022LISA: Learning Interpretable Skill Abstractions from Languagecited by 30
  32. 2022Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applicationscited by 28
  33. 2025SIMA 2: A Generalist Embodied Agent for Virtual Worldscited by 28
  34. 2021Language Models are Few-Shot Butlerscited by 27
  35. 2021LILA: Language-Informed Latent Actionscited by 27
  36. 2023Programmatically Grounded, Compositionally Generalizable Robotic Manipulationcited by 26
  37. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  38. 2022EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RLcited by 23

50 most cited of 154 All 154 (JSON)