mlsanityData to 14 Oct 2026

Neuro-Symbolic Reinforcement Learning with First-Order Logic

arXiv 2110.10963 ↗First posted 21 Oct 2021cs.AI cs.CL cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 21 Oct 2021.

Builds on

16 of 21 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2018TextWorld: A Learning Environment for Text-based Gamescited by 310
  5. 2019Neural Logic Machinescited by 145
  6. 2020Logical Neural Networkscited by 119
  7. 2015Language Understanding for Text-based Games Using Deep Reinforcement Learningcited by 71
  8. 2018Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learningcited by 53
  9. 2020Learning Dynamic Belief Graphs to Generalize on Text-Based Gamescited by 49
  10. 2020Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselinescited by 37
  11. 2018Counting to Explore and Generalize in Text-based Gamescited by 36
  12. 2019LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Gamescited by 17
4 more
  1. 2018Internal Model from Observations for Reward Shapingcited by 11
  2. 2021Reinforcement Learning with External Knowledge by using Logical Neural Networkscited by 10
  3. 2020Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Gamescited by 7
  4. 2018DAQN: Deep Auto-encoder and Q-Networkcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 7; 2024: 12; 2025: 4; 2026: 1.

30 papers.

Sort:

By area:

  1. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 46
  2. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 38
  3. 2023Introspective Tips: Large Language Model for In-Context Decision Makingcited by 28
  4. 2023Neurosymbolic Reinforcement Learning and Planning: A Surveycited by 24
  5. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  6. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  7. 2022TextWorldExpress: Simulating Text Games at One Million Steps Per Secondcited by 13
  8. 2022Learning to Follow Instructions in Text-Based Gamescited by 12
  9. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  10. 2022Behavior Cloned Transformers are Neurosymbolic Reasonerscited by 10
  11. 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trendscited by 10
  12. 2022Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Searchcited by 9
18 more
  1. 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulationcited by 8
  2. 2023Towards Safe Autonomous Driving Policies using a Neuro-Symbolic Deep Reinforcement Learning Approachcited by 7
  3. 2024Temporal Knowledge-Graph Memory in a Partially Observable Environmentcited by 5
  4. 2023Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learningcited by 4
  5. 2025Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policiescited by 4
  6. 2024EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learningcited by 3
  7. 2024SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Taskscited by 3
  8. 2024A Synergistic Approach In Network Intrusion Detection By Neurosymbolic AIcited by 2
  9. 2024Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanationscited by 2
  10. 2022Commonsense Knowledge from Scene Graphs for Textual Environmentscited by 1
  11. 2023Symbolic Imitation Learning: From Black-Box to Explainable Driving Policiescited by 1
  12. 2023Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discoverycited by 1
  13. 2024Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networkscited by 1
  14. 2022DiffG-RL: Leveraging Difference between State and Common Sensecited by 0
  15. 2024Bridging the Gap: Representation Spaces in Neuro-Symbolic AIcited by 0
  16. 2025Hierarchical Reinforcement Learning with Targeted Causal Interventionscited by 0
  17. 2025Disentangling Neural Disjunctive Normal Form Modelscited by 0
  18. 2026GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learningcited by 0