mlsanityData to 14 Oct 2026

Deep Reinforcement Learning with a Natural Language Action Space

arXiv 1511.04636 ↗First posted 14 Nov 2015cs.AI cs.CL cs.LGcited by 88

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased action descriptions show that the model is extracting meaning rather than simply memorizing strings of text.

Key facts. Cited by 88 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 20; 2022: 11; 2023: 20; 2024: 18; 2025: 10; 2026: 7.

88 papers.

Sort:

By area:

  1. 2024Understanding the planning of LLM agents: A surveycited by 421
  2. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  3. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
  4. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 95
  5. 2021What Would Jiminy Cricket Do? Towards Agents That Behave Morallycited by 57
  6. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 57
  7. 2024Value Augmented Sampling for Language Model Alignment and Personalizationcited by 49
  8. 2024Agent-Oriented Planning in Multi-Agent Systemscited by 36
  9. 2021Recomposing the Reinforcement Learning Building Blocks with Hypernetworkscited by 35
  10. 2022Aligning to Social Norms and Values in Interactive Narrativescited by 32
  11. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  12. 2021Survey on reinforcement learning for language processingcited by 31
38 more
  1. 2021Learning Knowledge Graph-based World Models of Textual Environmentscited by 31
  2. 2023Augmenting Autotelic Agents with Large Language Modelscited by 30
  3. 2021Language Models are Few-Shot Butlerscited by 27
  4. 2024ChatShop: Interactive Information Seeking with Language Agentscited by 24
  5. 2022Multi-Stage Episodic Control for Strategic Exploration in Text Gamescited by 22
  6. 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agentscited by 22
  7. 2021Pre-trained Language Models as Prior Knowledge for Playing Text-based Gamescited by 21
  8. 2021Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agentscited by 20
  9. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  10. 2021Contrastive Reinforcement Learning of Symbolic Reasoning Domainscited by 17
  11. 2021A Systematic Survey of Text Worlds as Embodied Natural Language Environmentscited by 17
  12. 2021Training Value-Aligned Reinforcement Learning Agents Using a Normative Priorcited by 14
  13. 2021A Survey of Text Games for Reinforcement Learning informed by Natural Languagecited by 14
  14. 2020Offline Reinforcement Learning from Human Feedback in Real-World Sequence-to-Sequence Taskscited by 12
  15. 2022Learning to Follow Instructions in Text-Based Gamescited by 12
  16. 2024Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrationscited by 12
  17. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
  18. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  19. 2023Knowledge-enhanced Agents for Interactive Text Gamescited by 10
  20. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  21. 2026Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agentscited by 9
  22. 2021Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memorycited by 8
  23. 2021Case-based Reasoning for Better Generalization in Textual Reinforcement Learningcited by 8
  24. 2023Minimax Optimal Q Learning with Nearest Neighborscited by 8
  25. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Modelscited by 8
  26. 2019Action Assembly: Sparse Imitation Learning for Text Based Games with Combinatorial Action Spacescited by 7
  27. 2021Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Playcited by 7
  28. 2024Grounded Language Agent for Product Search via Intelligent Web Interactionscited by 7
  29. 2026When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Trainingcited by 7
  30. 2026SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Trainingcited by 6
  31. 2021Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flowcited by 5
  32. 2021Learning and Executing Re-usable Behaviour Trees from Natural Language Instructioncited by 5
  33. 2024Stochastic Q-learning for Large Discrete Action Spacescited by 5
  34. 2025A Generalist Hanabi Agentcited by 5
  35. 2021Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agentscited by 4
  36. 2023Dynamic Neighborhood Construction for Structured Large Discrete Action Spacescited by 4
  37. 2023Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learningcited by 4
  38. 2024Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Modelscited by 4

50 most cited of 88 All 88 (JSON)