Transparency and Explanation in Deep Reinforcement Learning Neural Networks
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i.e. the system should be transparent. System transparency enables humans to form coherent explanations of the system's decisions and actions. Transparency is important not only for user trust, but also for software debugging and certification. In recent years, Deep Neural Networks have made great advances in multiple application areas. However, deep neural networks are opaque. In this paper, we report on work in transparency in Deep Reinforcement Learning Networks (DRLN). Such networks have been extremely successful in accurately learning action control in image input domains, such as Atari games. In this paper, we propose a novel and general method that (a) incorporates explicit object recognition processing into deep reinforcement learning models, (b) forms the basis for the development of "object saliency maps", to provide visualization of internal states of DRLNs, thus enabling the formation of explanations and (c) can be incorporated in any existing deep reinforcement learning framework. We present computational results and human experiments to evaluate our approach.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 1×
“Ribeiro et al. (Ribeiro, Singh, and Guestrin 2016) proposed a method to explain the prediction of any classifier by local exploration, and apply it on image and text classification.”
MethodTrust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1×
“The excellent performance of convolutional neural networks over the past several years has dramatically improved object recognition (Krizhevsky, Sutskever, and Hinton 2012),(Sermanet et al. 2013), (Hinton et al. 2012), (Szegedy et al. 2015), (Song et al. 2014).”
BackgroundDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680
Building high-level features using large scale unsupervised learning
Le, Q. V. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6639343 · Cited by 1,695 · cited 1×
“It was later employed by (Le 2013) to visualize the class models, captured by a deep unsupervised auto-encoder.”
MethodIntelligent agent transparency in human–agent teaming for multi-UxV management
Mercado, J. E., Rupp, M. A., Chen, J. Y. C., Barnes, M. J., Barber, D., & Procci, K. (2016) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720815621206 · Cited by 403 · cited 2×
“This new model can be incorporated with most existing deep RL frameworks such as DQN (Mnih et al. 2015) and A3C (Mnih et al. 2016).”
MethodTransparency in a Human-Machine Context: Approaches for Fostering Shared Awareness/Intent
Lyons, J. B., & Havig, P. R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-07458-0_18 · Cited by 96
Cited by
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond
Li, X., Xiong, H., Li, X., Wu, X., Zhang, X., Liu, J., Bian, J., & Dou, D. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01756-8 · Cited by 497
Explainable Deep Learning: A Field Guide for the Uninitiated
Ras, G., Xie, N., Van Gerven, M., & Doran, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13200 · Cited by 446
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
Zhang, Z., Hamadi, H. A., Damiani, E., Yeun, C. Y., & Taher, F. (2022) · IEEE Access · doi:10.1109/access.2022.3204051 · Cited by 450
An Explainable Machine Learning Framework for Intrusion Detection Systems
Wang, M., Zheng, K., Yang, Y., & Wang, X. (2020) · IEEE Access · doi:10.1109/access.2020.2988359 · Cited by 355
Singhal, A., Neveditsin, N., Tanveer, H., & Mago, V. (2024) · JMIR Medical Informatics · doi:10.2196/50048 · Cited by 172
“…is accomplished by offering clear, understandable explanations of the system’s functionality and making its data and algorithms openly available [65]; (4) stakeholder engagement—this involves the active participation of a diverse group of stakeholders, including users, developers, and experts,…”
Background
Metadata
- Authors
- Iyer, R., Li, Y., Li, H., Lewis, M., Sundar, R., & Sycara, K.
- Venue
- Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society
- Publisher
- ACM
- Published
- 2018-12-27
- Pages
- 144-150
- ISSN
- 3065-8365 (ISSN-L)
- OpenAlex
- W2891830784
- Cited by
- 145
- References
- 9
- FWCI
- 6.87
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Transparency and Explanation in Deep Reinforcement Learning Neural Networks. https://app.cochat.ai/papers/10.1145/3278721.3278776
- The paper
- Iyer, R., Li, Y., Li, H., Lewis, M., Sundar, R., & Sycara, K. (2018). Transparency and Explanation in Deep Reinforcement Learning Neural Networks. Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. https://doi.org/10.1145/3278721.3278776
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.