mlsanityData to 14 Oct 2026

Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning Programs

arXiv 2406.19812 ↗First posted 28 Jun 2024cs.SE cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Reinforcement Learning (RL) has gained significant attention across various domains. However, the increasing complexity of RL programs presents testing challenges, particularly the oracle problem: defining the correctness of the RL program. Conventional human oracles struggle to cope with the complexity, leading to inefficiencies and potential unreliability in RL testing. To alleviate this problem, we propose an automated oracle approach that leverages RL properties using fuzzy logic. Our oracle quantifies an agent's behavioral compliance with reward policies and analyzes its trend over training episodes. It labels an RL program as "Buggy" if the compliance trend violates expectations derived from RL characteristics. We evaluate our oracle on RL programs with varying complexities and compare it with human oracles. Results show that while human oracles perform well in simpler testing scenarios, our fuzzy oracle demonstrates superior performance in complex environments. The proposed approach shows promise in addressing the oracle problem for RL testing, particularly in complex cases where manual testing falls short. It offers a potential solution to improve the efficiency, reliability, and scalability of RL program testing. This research takes a step towards automated testing of RL programs and highlights the potential of fuzzy logic-based oracles in tackling the oracle problem.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 11 of its 31 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

11 of 31 references.

References · 11

  1. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  2. 2017Deep Reinforcement Learning: An Overviewcited by 333
  3. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 218
  4. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  5. 2018On Testing Machine Learning Programscited by 48
  6. 2020Model-based Reinforcement Learning: A Surveycited by 39
  7. 2021DeepLocalize: Fault Localization for Deep Neural Networkscited by 38
  8. 2021Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approachcited by 18
  9. 2022Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzingcited by 16
  10. 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 13
  11. 2019MDP Playground: An Analysis and Debug Testbed for Reinforcement Learningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
  2. 2026Fuzzy Logic Theory-based Adaptive Reward Shaping for Robust Reinforcement Learning (FARS)
  3. 2025Reward Compatibility: A Framework for Inverse RL
  4. 2026Reinforcement Learning from Human Feedback: A Statistical Perspective
  5. 2025RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
  6. 2025ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning
  7. 2025Reducing Reward Dependence in RL Through Adaptive Confidence Discounting
  8. 2021A Validation Tool for Designing Reinforcement Learning Environments