mlsanityData to 14 Oct 2026

Using Part-based Representations for Explainable Deep Reinforcement Learning

arXiv 2408.11455 ↗First posted 21 Aug 2024cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obtained from feature representations through simple addition. However, training a part-based learning model presents challenges, particularly in enforcing non-negative constraints on the model's parameters, which can result in training difficulties such as instability and convergence issues. Moreover, applying such approaches in Deep Reinforcement Learning (RL) is even more demanding due to the inherent instabilities that impact many optimization methods. In this paper, we propose a non-negative training approach for actor models in RL, enabling the extraction of part-based representations that enhance interpretability while adhering to non-negative constraints. To this end, we employ a non-negative initialization technique, as well as a modified sign-preserving training method, which can ensure better gradient flow compared to existing approaches. We demonstrate the effectiveness of the proposed approach using the well-known Cartpole benchmark.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 26 references that are in the map. First posted on arXiv 21 Aug 2024.

Builds on

12 of 26 references.

References · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  6. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  7. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  8. 2018Learning Deep Representations with Probabilistic Knowledge Transfercited by 213
  9. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  10. 2019How Case Based Reasoning Explained Neural Networks: An XAI Survey of Post-Hoc Explanation-by-Example in ANN-CBR Twinscited by 20
  11. 2018Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Datacited by 9
  12. 2016Deep Learning of Part-based Representation of Data Using Sparse Autoencoders with Nonnegativity Constraintscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Explainable Deep Reinforcement Learning
  2. 2025From Explainability to Interpretability: Interpretable Policies in Reinforcement Learning Via Model Explanation
  3. 2026Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
  4. 2025Explainable RL Policies by Distilling to Locally-Specialized Linear Policies with Voronoi State Partitioning
  5. 2023Transformers in Reinforcement Learning: A Survey
  6. 2025A Survey of State Representation Learning for Deep Reinforcement Learning
  7. 2026Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
  8. 2024Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies