On the role of tracking in stationary environments
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
It is often thought that learning algorithms that track the best solution, as opposed to converging to it, are important only on nonstationary problems. We present three results suggesting that this is not so. First we illustrate in a simple concrete example, the Black and White problem, that tracking can perform better than any converging algorithm on a stationary problem. Second, we show the same point on a larger, more realistic problem, an application of temporal difference learning to computer Go. Our third result suggests that tracking in stationary problems could be important for metalearning research (e.g., learning to learn, feature selection, transfer). We apply a metalearning algorithm for step-size adaptation, IDBD (Sutton, 1992a), to the Black and White problem, showing that meta-learning has a dramatic long-term effect on performance whereas, on an analogous converging problem, meta-learning has only a small second-order effect. This small result suggests a way of eventually overcoming a major obstacle to meta-learning research: the lack of an independent methodology for task selection.
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
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148 · cited 3×
“Thus, we use equations 2 and 3, where the target at time t is set according to the T D(0) algorithm (Sutton, 1988): zt = rt+1 + V (st+1).”
MethodSelf-citationTemporal difference learning and TD-Gammon
Tesauro, G. (1995) · Communications of the ACM · doi:10.1145/203330.203343 · Cited by 1,618
Cited by
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160
Transfer Learning for Reinforcement Learning Domains: A Survey
Taylor, M. E., & Stone, P. (2009) · doi:10.5555/1577069.1755839 · Cited by 1,488
Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective
Singh, S., Lewis, R. L., Barto, A. G., & Sorg, J. (2010) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2010.2051031 · Cited by 417
(2013) · Cited by 290
Model-Free reinforcement learning with continuous action in practice
Degris, T., Pilarski, P. M., & Sutton, R. S. (2012) · 2012 American Control Conference (ACC) · doi:10.1109/acc.2012.6315022 · Cited by 239
Self-citation
Metadata
- Authors
- Sutton, R. S., Koop, A., & Silver, D.
- Venue
- Proceedings of the 24th international conference on Machine learning
- Publisher
- ACM
- Published
- 2007-06-20
- Pages
- 871-878
- OpenAlex
- W2163533082
- Cited by
- 63
- References
- 2
- FWCI
- 1.95
- Type
- conference paper
- Language
- en
- Open access
- closed
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: On the role of tracking in stationary environments. https://app.cochat.ai/papers/10.1145/1273496.1273606
- The paper
- Sutton, R. S., Koop, A., & Silver, D. (2007). On the role of tracking in stationary environments. Proceedings of the 24th international conference on Machine learning. https://doi.org/10.1145/1273496.1273606
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.