mlsanityData to 7 Oct 2026

Towards Better Interpretability in Deep Q-Networks

arXiv 1809.05630 ↗First posted 15 Sep 2018cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model's behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-art deep Q-learning models. However, results suggest that the features extracted by the neural network are extremely shallow and subsequent testing using out-of-sample examples shows that the agent can easily overfit to trajectories seen during training.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 7; 2023: 6; 2024: 2; 2025: 2.

22 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  3. 2021A Survey on Interpretable Reinforcement Learningcited by 70
  4. 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
  5. 2021Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methodscited by 31
  6. 2022A Survey of Explainable Reinforcement Learningcited by 31
  7. 2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Datacited by 19
  8. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  9. 2021Deep Interpretable Models of Theory of Mindcited by 13
  10. 2022Time-Efficient Reward Learning via Visually Assisted Cluster Rankingcited by 8
  11. 2023A Closer Look at Reward Decomposition for High-Level Robotic Explanationscited by 7
  12. 2021Temporal-Spatial Causal Interpretations for Vision-Based Reinforcement Learningcited by 6
10 more
  1. 2022ProtoX: Explaining a Reinforcement Learning Agent via Prototypingcited by 4
  2. 2022A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challengescited by 3
  3. 2023Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learningcited by 3
  4. 2024Learning Goal-Conditioned Representations for Language Reward Modelscited by 2
  5. 2021An Interpretable Framework for Drug-Target Interaction with Gated Cross Attentioncited by 1
  6. 2023XDQN: Inherently Interpretable DQN through Mimickingcited by 1
  7. 2023FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Maskscited by 1
  8. 2022Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoderscited by 0
  9. 2024Why the Agent Made that Decision: Contrastive Explanation Learning for Reinforcement Learningcited by 0
  10. 2025Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learningcited by 0