mlsanityData to 7 Oct 2026

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

arXiv 2001.08837 ↗First posted 23 Jan 2020cs.LG cs.AI cs.CLcited by 80

Not on the map. Why?

Abstract (arXiv)

Interactive Fiction games are text-based simulations in which an agent interacts with the world purely through natural language. They are ideal environments for studying how to extend reinforcement learning agents to meet the challenges of natural language understanding, partial observability, and action generation in combinatorially-large text-based action spaces. We present KG-A2C, an agent that builds a dynamic knowledge graph while exploring and generates actions using a template-based action space. We contend that the dual uses of the knowledge graph to reason about game state and to constrain natural language generation are the keys to scalable exploration of combinatorially large natural language actions. Results across a wide variety of IF games show that KG-A2C outperforms current IF agents despite the exponential increase in action space size.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 16; 2023: 22; 2024: 13; 2025: 9; 2026: 3.

80 papers.

Sort:

By area:

  1. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  2. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 244
  3. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 174
  4. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  5. 2024A Survey on Large Language Model-Based Game Agentscited by 106
  6. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  7. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88
  8. 2021What Would Jiminy Cricket Do? Towards Agents That Behave Morallycited by 57
  9. 2024Can Language Models Serve as Text-Based World Simulators?cited by 50
  10. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 35
  11. 2022Aligning to Social Norms and Values in Interactive Narrativescited by 32
  12. 2021Learning Knowledge Graph-based World Models of Textual Environmentscited by 31
38 more
  1. 2023Interactive Natural Language Processingcited by 31
  2. 2023Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questionscited by 30
  3. 2023Introspective Tips: Large Language Model for In-Context Decision Makingcited by 28
  4. 2022Multi-Stage Episodic Control for Strategic Exploration in Text Gamescited by 22
  5. 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agentscited by 22
  6. 2021Pre-trained Language Models as Prior Knowledge for Playing Text-based Gamescited by 21
  7. 2021Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agentscited by 20
  8. 2022Reinforcement learning on graphs: A surveycited by 18
  9. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  10. 2021Inherently Explainable Reinforcement Learning in Natural Languagecited by 16
  11. 2021Training Value-Aligned Reinforcement Learning Agents Using a Normative Priorcited by 14
  12. 2021A Survey of Text Games for Reinforcement Learning informed by Natural Languagecited by 14
  13. 2021Goal-Directed Story Generation: Augmenting Generative Language Models with Reinforcement Learningcited by 14
  14. 2022TextWorldExpress: Simulating Text Games at One Million Steps Per Secondcited by 12
  15. 2022Learning to Follow Instructions in Text-Based Gamescited by 12
  16. 2021Modeling Worlds in Textcited by 11
  17. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
  18. 2025TextQuests: How Good are LLMs at Text-Based Video Games?cited by 11
  19. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  20. 2022Asking for Knowledge: Training RL Agents to Query External Knowledge Using Languagecited by 10
  21. 2022Behavior Cloned Transformers are Neurosymbolic Reasonerscited by 10
  22. 2023Knowledge-enhanced Agents for Interactive Text Gamescited by 10
  23. 2023Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challengescited by 10
  24. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  25. 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
  26. 2025TALES: Text Adventure Learning Environment Suitecited by 9
  27. 2025LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Studycited by 9
  28. 2021Case-based Reasoning for Better Generalization in Textual Reinforcement Learningcited by 8
  29. 2023Dialogue Shaping: Empowering Agents through NPC Interactioncited by 8
  30. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Modelscited by 8
  31. 2021Detecting and Adapting to Novelty in Gamescited by 7
  32. 2023Story Shaping: Teaching Agents Human-like Behavior with Storiescited by 7
  33. 2021Generalising Discrete Action Spaces with Conditional Action Treescited by 6
  34. 2023Thespian: Multi-Character Text Role-Playing Game Agentscited by 6
  35. 2024LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectivescited by 6
  36. 2024Temporal Knowledge-Graph Memory in a Partially Observable Environmentcited by 5
  37. 2021Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agentscited by 4
  38. 2023Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learningcited by 4

50 most cited of 80 All 80 (JSON)