Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
During training, model-free reinforcement learning (RL) systems can explore actions that lead to harmful or costly consequences. Having a human "in the loop'' and ready to intervene at all times can prevent these mistakes, but is prohibitively expensive for current algorithms. We explore how human oversight can be combined with a supervised learning system to prevent catastrophic events during training. We demonstrate this scheme on Atari games, with a Deep RL agent being overseen by a human for four hours. When the class of catastrophes is simple, we are able to prevent all catastrophes without affecting the agent's learning (whereas an RL baseline fails due to catastrophic forgetting).
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
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
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
Deep Reinforcement Learning with Double Q-Learning
Van Hasselt, H., Guez, A., & Silver, D. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10295 · Cited by 3,318
The Arcade Learning Environment: An Evaluation Platform for General Agents
Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3912 · Cited by 2,161
Concrete Problems in AI Safety
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016) · arXiv · doi:10.48550/arxiv.1606.06565 · Cited by 1,314
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058
Blundell, C., Uria, B., Pritzel, A., Li, Y., Ruderman, A., Leibo, J. Z., Rae, J., Wierstra, D., & Hassabis, D. (2016) · arXiv · doi:10.48550/arxiv.1606.04460 · Cited by 162
Cited by
Exploration in deep reinforcement learning: A survey
Ladosz, P., Weng, L., Kim, M., & Oh, H. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.03.003 · Cited by 525
Residual Reinforcement Learning for Robot Control
Johannink, T., Bahl, S., Nair, A., Luo, J., Kumar, A., Loskyll, M., Ojea, J. A., Solowjow, E., & Levine, S. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794127 · Cited by 480
Software Engineering for AI-Based Systems: A Survey
Martínez-Fernández, S., Bogner, J., Franch, X., Oriol, M., Siebert, J., Trendowicz, A., Vollmer, A. M., & Wagner, S. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3487043 · Cited by 335
Leike, J., Martic, M., Krakovna, V., Ortega, P. A., Everitt, T., Lefrancq, A., Orseau, L., & Legg, S. (2017) · arXiv · doi:10.48550/arxiv.1711.09883 · Cited by 240
Wu, J., Huang, Z., Hu, Z., & Lv, C. (2023) · Engineering · doi:10.1016/j.eng.2022.05.017 · Cited by 205
Metadata
- Authors
- Saunders, W., Sastry, G., Stuhlmüller, A., & Evans, O.
- Venue
- International Joint Conference on Autonomous Agents and Multiagent Systems
- Publisher
- IEEE Computer Society
- Published
- 2018-07-09
- Pages
- 2067-2069
- ISSN
- 1548-8403 (ISSN-L)
- 1558-2914
- OpenAlex
- W2964273112
- Cited by
- 157
- References
- 7
- FWCI
- 10.09
- Type
- conference paper
- Language
- en
- Open access
- green
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: Trial without Error: Towards Safe Reinforcement Learning via Human Intervention. https://app.cochat.ai/papers/10.65109/mzmg4429
- The paper
- Saunders, W., Sastry, G., Stuhlmüller, A., & Evans, O. (2018). Trial without Error: Towards Safe Reinforcement Learning via Human Intervention. International Joint Conference on Autonomous Agents and Multiagent Systems. https://doi.org/10.65109/mzmg4429
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.