mlsanityData to 14 Oct 2026

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

arXiv 2010.03790 ↗First posted 8 Oct 2020cs.AI cs.CL cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making. In this paper, we examine the problem of infusing RL agents with commonsense knowledge. Such knowledge would allow agents to efficiently act in the world by pruning out implausible actions, and to perform look-ahead planning to determine how current actions might affect future world states. We design a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances. We also introduce several baseline RL agents which track the sequential context and dynamically retrieve the relevant commonsense knowledge from ConceptNet. We show that agents which incorporate commonsense knowledge in TWC perform better, while acting more efficiently. We conduct user-studies to estimate human performance on TWC and show that there is ample room for future improvement.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 8; 2023: 8; 2024: 8; 2025: 1; 2026: 2.

37 papers.

Sort:

By area:

  1. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 327
  2. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
  3. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 102
  4. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 38
  5. 2022Aligning to Social Norms and Values in Interactive Narrativescited by 32
  6. 2021Learning Knowledge Graph-based World Models of Textual Environmentscited by 31
  7. 2021Neuro-Symbolic Reinforcement Learning with First-Order Logiccited by 30
  8. 2021A Survey of Text Games for Reinforcement Learning informed by Natural Languagecited by 14
  9. 2022TextWorldExpress: Simulating Text Games at One Million Steps Per Secondcited by 13
  10. 2021Modeling Worlds in Textcited by 11
  11. 2021How to Query Language Models?cited by 11
  12. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
25 more
  1. 2026World of Workflows: A Benchmark for Bringing World Models to Enterprise Systemscited by 11
  2. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  3. 2022Behavior Cloned Transformers are Neurosymbolic Reasonerscited by 10
  4. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  5. 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
  6. 2021Case-based Reasoning for Better Generalization in Textual Reinforcement Learningcited by 8
  7. 2023Conceptual Reinforcement Learning for Language-Conditioned Taskscited by 8
  8. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Modelscited by 8
  9. 2021LOA: Logical Optimal Actions for Text-based Interaction Gamescited by 6
  10. 2021Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agentscited by 4
  11. 2023Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoningcited by 4
  12. 2023Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learningcited by 4
  13. 2024Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfittingcited by 4
  14. 2024EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learningcited by 3
  15. 2022Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methodscited by 2
  16. 2023Polar Ducks and Where to Find Them: Enhancing Entity Linking with Duck Typing and Polar Box Embeddingscited by 2
  17. 2023ScriptWorld: Text Based Environment For Learning Procedural Knowledgecited by 2
  18. 2024ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about Actionscited by 2
  19. 2024Positive Experience Reflection for Agents in Interactive Text Environmentscited by 2
  20. 2022Commonsense Knowledge from Scene Graphs for Textual Environmentscited by 1
  21. 2023Heterogeneous Knowledge for Augmented Modular Reinforcement Learningcited by 1
  22. 2023Self-Supervised Behavior Cloned Transformers are Path Crawlers for Text Gamescited by 1
  23. 2022DiffG-RL: Leveraging Difference between State and Common Sensecited by 0
  24. 2024On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learningcited by 0
  25. 2026The Mechanism Matters: When Knowledge Graphs Help Reinforcement Learningcited by 0