Sample-based learning and search with permanent and transient memories
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
We present a reinforcement learning architecture, Dyna-2, that encompasses both sample-based learning and sample-based search, and that generalises across states during both learning and search. We apply Dyna-2 to high performance Computer Go. In this domain the most successful planning methods are based on sample-based search algorithms, such as UCT, in which states are treated individually, and the most successful learning methods are based on temporal-difference learning algorithms, such as Sarsa, in which linear function approximation is used. In both cases, an estimate of the value function is formed, but in the first case it is transient, computed and then discarded after each move, whereas in the second case it is more permanent, slowly accumulating over many moves and games. The idea of Dyna-2 is for the transient planning memory and the permanent learning memory to remain separate, but for both to be based on linear function approximation and both to be updated by Sarsa. To apply Dyna-2 to 9x9 Computer Go, we use a million binary features in the function approximator, based on templates matching small fragments of the board. Using only the transient memory, Dyna-2 performed at least as well as UCT. Using both memories combined, it significantly outperformed UCT. Our program based on Dyna-2 achieved a higher rating on the Computer Go Online Server than any handcrafted or traditional search based program.
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
Finite-time Analysis of the Multiarmed Bandit Problem
Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002) · Machine Learning · doi:10.1023/a:1013689704352 · Cited by 6,033
Learning to predict by the methods of temporal differences
Sutton, R. S. (1988) · Machine Learning · doi:10.1007/bf00115009 · Cited by 5,148 · cited 2×
“The TD(.) algorithm (Sutton, 1988) estimates the value of the current state from the value of subsequent states.”
BackgroundSelf-citationOn-line policy improvement using Monte-Carlo search
Tesauro, G., & Galperin, G. R. (2025) · arXiv · doi:10.48550/arxiv.2501.05407 · Cited by 209
Cited by
A Survey of Monte Carlo Tree Search Methods
Browne, C. B., Powley, E., Whitehouse, D., Lucas, S. M., Cowling, P. I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., & Colton, S. (2012) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2012.2186810 · Cited by 2,970
“This opening book improved the playing strength of the program and was reported to be consistent with expert Go knowledge in some cases.”
BackgroundMethodDeep reinforcement learning for autonomous driving: A survey
Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A. A. A., Yogamani, S., & Perez, P. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3054625 · Cited by 2,342
Dolan, R. J., & Dayan, P. (2013) · Neuron · doi:10.1016/j.neuron.2013.09.007 · Cited by 977
Deep Reinforcement Learning: A Survey
Wang, X., Wang, S., Liang, X., Zhao, D., Huang, J., Xu, X., Dai, B., & Miao, Q. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3207346 · Cited by 972
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning
Nagabandi, A., Kahn, G., Fearing, R. S., & Levine, S. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8463189 · Cited by 848
Metadata
- Authors
- Silver, D., Sutton, R. S., & Müller, M.
- Venue
- Proceedings of the 25th international conference on Machine learning - ICML '08
- Publisher
- ACM Press
- Published
- 2008
- Pages
- 968-975
- OpenAlex
- W2097778153
- Cited by
- 107
- References
- 3
- FWCI
- 3.97
- 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
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.