Open Access
| Issue |
ITM Web Conf.
Volume 78, 2025
International Conference on Computer Science and Electronic Information Technology (CSEIT 2025)
|
|
|---|---|---|
| Article Number | 01019 | |
| Number of page(s) | 11 | |
| Section | Deep Learning and Reinforcement Learning – Theories and Applications | |
| DOI | https://doi.org/10.1051/itmconf/20257801019 | |
| Published online | 08 September 2025 | |
- Saito, Y., Aihara, S., Matsutani, M., & Narita, Y.: 'A Large-scale Dataset for Decision Making Algorithms', 2021 [Google Scholar]
- Granmo, O.C.: 'Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton', Int. J. Intell. Comput. Cybern., 2010, 3, (2), pp. 207–234 [Google Scholar]
- Lattimore, T., Szepesvári, C.: 'Bandit Algorithms' (Cambridge University Press, 2020) [Google Scholar]
- Auer, P., Cesa-Bianchi, N., Fischer, P.: 'Finite-time analysis of the multiarmed bandit problem', Mach. Learn., 2002, 47, pp. 235–256 [CrossRef] [Google Scholar]
- Agrawal, S., Goyal, N.: 'Analysis of Thompson sampling for the multi-armed bandit problem'. Proc. Conf. Learning Theory, Edinburgh, UK, June 14, pp. 39 (JMLR Workshop and Conf. Proc.) [Google Scholar]
- Gittins, J.C.: 'Bandit processes and dynamic allocation indices', J. R. Stat. Soc. Series B Stat. Methodol., 1979, 41, (2), pp. 148–164 [Google Scholar]
- Chapelle, O., Li, L.: 'An empirical evaluation of Thompson sampling', Adv. Neural Inf. Process. Syst., 2011, 24 [Google Scholar]
- Kaufmann, E., Cappe, O., Garivier, A.: 'Thompson sampling: An asymptotically optimal finite-time analysis'. Proc. Int. Conf. Algorithmic Learning Theory, Lyon, France, Oct. 14, pp. 199 [Google Scholar]
- Russo, D., Van Roy, B.: 'An information-theoretic analysis of Thompson sampling', J. Mach. Learn. Res., 2016, 17, (68), pp. 1–30 [Google Scholar]
- Ghosh, A., Chowdhury, S.R., Gopalan, A.: 'Misspecified linear bandits'. Proc. AAAI Conf. Artif. Intell., San Francisco, CA, USA, Feb. 14, pp. 31 [Google Scholar]
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.