The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
An analysis of temporal-difference learning with function approximation
Open accessAbstract
We discuss the temporal-difference learning algorithm, as applied to approximating the cost-to-go function of an infinite-horizon discounted Markov chain. The algorithm we analyze updates parameters of a linear function approximator online during a single endless trajectory of an irreducible aperiodic Markov chain with a finite or infinite state space. We present a proof of convergence (with probability one), a characterization of the limit of convergence, and a bound on the resulting approximation error. Furthermore, our analysis is based on a new line of reasoning that provides new intuition about the dynamics of temporal-difference learning. In addition to proving new and stronger positive results than those previously available, we identify the significance of online updating and potential hazards associated with the use of nonlinear function approximators. First, we prove that divergence may occur when updates are not based on trajectories of the Markov chain. This fact reconciles positive and negative results that have been discussed in the literature, regarding the soundness of temporal-difference learning. Second, we present an example illustrating the possibility of divergence when temporal difference learning is used in the presence of a nonlinear function approximator.
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
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
(1995) · Cited by 10,558
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148
(2012) · Encyclopedia of the Sciences of Learning · doi:10.1007/978-1-4419-1428-6_5086 · Cited by 3,515
Adaptive Algorithms and Stochastic Approximations
Benveniste, A., Métivier, M., & Priouret, P. (1990) · Springer eBooks · doi:10.1007/978-3-642-75894-2 · Cited by 2,006
Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
Sutton, R. S. (1995) · Cited by 1,072
(2011) · Encyclopedia of Machine Learning · doi:10.1007/978-0-387-30164-8_588 · Cited by 950
Residual Algorithms: Reinforcement Learning with Function Approximation
Baird, L. (1995) · Machine Learning Proceedings 1995 · doi:10.1016/b978-1-55860-377-6.50013-x · Cited by 918
On the Convergence of Stochastic Iterative Dynamic Programming Algorithms
Jaakkola, T., Jordan, M. I., & Singh, S. P. (1994) · Neural Computation · doi:10.1162/neco.1994.6.6.1185 · Cited by 770
Reinforcement learning with replacing eligibility traces
Singh, S. P., & Sutton, R. S. (1996) · Machine Learning · doi:10.1007/bf00114726 · Cited by 575
Generalization in Reinforcement Learning: Safely Approximating the Value Function
Boyan, J. A., & Moore, A. (1994) · Cited by 508
Asynchronous stochastic approximation and Q-learning
Tsitsiklis, J. N. (1994) · Machine Learning · doi:10.1007/bf00993306 · Cited by 453
Self-citationStable Function Approximation in Dynamic Programming
Gordon, G. J. (1995) · Machine Learning Proceedings 1995 · doi:10.1016/b978-1-55860-377-6.50040-2 · Cited by 446
Feature-based methods for large scale dynamic programming
Tsitsiklis, J. N., & van Roy, B. (1996) · Machine Learning · doi:10.1007/bf00114724 · Cited by 432
Self-citationThe convergence of TD(?) for general ?
Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992701 · Cited by 275
Reinforcement Learning with Soft State Aggregation
Singh, S. P., Jaakkola, T., & Jordan, M. I. (1994) · Cited by 274
TD(λ) Converges with Probability 1
Dayan, P., & Sejnowski, T. J. (1994) · Machine Learning · doi:10.1023/a:1022657612745 · Cited by 169
Cited by
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
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
Deep Reinforcement Learning: A Brief Survey
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2743240 · Cited by 4,733
A Brief Survey of Deep Reinforcement Learning
Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharath, A. A. (2017) · arXiv · doi:10.48550/arxiv.1708.05866 · Cited by 4,733
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
Metadata
- Authors
- Tsitsiklis, J. N., & Van Roy, B.
- Venue
- IEEE Transactions on Automatic Control
- Published
- 1997-05
- Volume
- 42
- Issue
- 5
- Pages
- 674-690
- ISSN
- 0018-9286 (ISSN-L)
- OpenAlex
- W2139418546
- Cited by
- 1,194
- References
- 18
- FWCI
- 20.45
- Type
- journal article
- 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
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.