mlsanityData to 7 Oct 2026

EXPIL: Explanatory Predicate Invention for Learning in Games

arXiv 2406.06107 ↗First posted 10 Jun 2024cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Recent research has attempted to address this issue by using the guidance of pretrained neural agents to encode logic-based policies, allowing for interpretable decisions. A drawback of such approaches is the requirement of large amounts of predefined background knowledge in the form of predicates, limiting its applicability and scalability. In this work, we propose a novel approach, Explanatory Predicate Invention for Learning in Games (EXPIL), that identifies and extracts predicates from a pretrained neural agent, later used in the logic-based agents, reducing the dependency on predefined background knowledge. Our experimental evaluation on various games demonstrate the effectiveness of EXPIL in achieving explainable behavior in logic agents while requiring less background knowledge.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 10 Jun 2024.

Builds on

21 of 46 references.

References · 21

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  3. 2017Robust Adversarial Reinforcement Learningcited by 439
  4. 2017Learning Explanatory Rules from Noisy Datacited by 210
  5. 2018Programmatically Interpretable Reinforcement Learningcited by 192
  6. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  7. 2019Neural Logic Reinforcement Learningcited by 53
  8. 2023Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstractioncited by 45
  9. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  10. 2023OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environmentscited by 30
  11. 2021Differentiable Inductive Logic Programming for Structured Examplescited by 26
  12. 2020Randomised Gaussian Process Upper Confidence Bound for Bayesian Optimisationcited by 22
9 more
  1. 2024Interpretable and Editable Programmatic Tree Policies for Reinforcement Learningcited by 18
  2. 2022Boosting Object Representation Learning via Motion and Object Continuitycited by 17
  3. 2024End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanationscited by 17
  4. 2017Mutual Alignment Transfer Learningcited by 16
  5. 2023Learning Differentiable Logic Programs for Abstract Visual Reasoningcited by 12
  6. 2019Learning higher-order logic programscited by 11
  7. 2024HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learningcited by 11
  8. 2021Predicate Invention by Learning From Failurescited by 9
  9. 2022Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Searchcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 0; 2026: 1.

5 papers.

  1. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  2. 2024Interpretable end-to-end Neurosymbolic Reinforcement Learning agentscited by 4
  3. 2024SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Taskscited by 3
  4. 2024OCALM: Object-Centric Assessment with Language Modelscited by 0
  5. 2026From Black Box to Executable Logic: Explainable Reinforcement Learning through Prolog Expert Systemscited by 0