Active Reward Learning
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
While reward functions are an essential component of many robot learning methods, defining such functions remains a hard problem in many practical applications.For tasks such as grasping, there are no reliable success measures available.Defining reward functions by hand requires extensive task knowledge and often leads to undesired emergent behavior.Instead, we propose to learn the reward function through active learning, querying human expert knowledge for a subset of the agent's rollouts.We introduce a framework, wherein a traditional learning algorithm interplays with the reward learning component, such that the evolution of the action learner guides the queries of the reward learner.We demonstrate results of our method on a robot grasping task and show that the learned reward function generalizes to a similar task.
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
Gaussian Processes in Machine Learning
Rasmussen, C. E. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-28650-9_4 · Cited by 5,397
Cited by
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
“These methods have not yet been tested with expressive function approximators such as deep neural networks, but this should be possible in principle for some of the methods, such as [151], which proposes a modification to policy gradient algorithms to optimize a risk-sensitive criterion.”
MethodDeep 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
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
Chen, X., Qu, G., Tang, Y., Low, S., & Li, N. (2022) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2022.3154718 · Cited by 415
Active Preference-Based Learning of Reward Functions
Sadigh, D., Dragan, A., Sastry, S., & Seshia, S. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.053 · Cited by 255
End-To-End Robotic Reinforcement Learning without Reward Engineering
Singh, A., Yang, L., Finn, C., & Levine, S. (2019) · Robotics: Science and Systems XV · doi:10.15607/rss.2019.xv.073 · Cited by 196
AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos
Smith, L., Dhawan, N., Zhang, M., Abbeel, P., & Levine, S. (2020) · Robotics: Science and Systems XVI · doi:10.15607/rss.2020.xvi.024 · Cited by 102
Incomplete Contracting and AI Alignment
Hadfield-Menell, D., & Hadfield, G. K. (2018) · doi:10.2139/ssrn.3165793 · Cited by 28
Human in the AI Loop via xAI and Active Learning for Visual Inspection
Rožanec, J. M., Montini, E., Cutrona, V., Papamartzivanos, D., Klemenčič, T., Fortuna, B., Mladenić, D., Veliou, E., Giannetsos, T., & Emmanouilidis, C. (2024) · Artificial Intelligence in Manufacturing · doi:10.1007/978-3-031-46452-2_22 · Cited by 17
Metadata
- Authors
- Daniel, C., Viering, M., Metz, J., Kroemer, O., & Peters, J.
- Venue
- Robotics: Science and Systems X
- Published
- 2014-07-12
- OpenAlex
- W218896052
- Cited by
- 86
- References
- 1
- FWCI
- 3.16
- Type
- conference paper
- Language
- en
- Open access
- gold
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
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.