Open Access
| Issue |
ITM Web Conf.
Volume 80, 2025
2025 2nd International Conference on Advanced Computer Applications and Artificial Intelligence (ACAAI 2025)
|
|
|---|---|---|
| Article Number | 02003 | |
| Number of page(s) | 10 | |
| Section | Reinforcement Learning, Bandits & Optimization | |
| DOI | https://doi.org/10.1051/itmconf/20258002003 | |
| Published online | 16 December 2025 | |
- A.N. Khiabani, B. Macq, Deep reinforcement learning for the expert advice multi- armed bandit. In Proc. IEEE EUROCON 2025 – 21st Int. Conf. Smart Technol. (IEEE, 2025). [Google Scholar]
- K. Sasaki, T. Mihana, K. Kanno, M. Naruse, A. Uchida, Experiment on decision making for multi-armed bandit problem using chaos and low frequency fluctuations in laser network. In Proc. Conf. Lasers Electro-Optics Pacific Rim (CLEO-PR) (IEEE, 2022). [Google Scholar]
- A. Slivkins, Book announcement: Introduction to multi-armed bandits. ACM SIGecom Exchanges 18, 28–30 (2020). [Google Scholar]
- V. Kuleshov, D. Precup, Algorithms for multi-armed bandit problems. CoRR abs/1402.6028 (2014). [Google Scholar]
- A. Yekkehkhany, R. Nagi, Risk-averse equilibria for vehicle navigation in stochastic congestion games. IEEE Trans. Intell. Transp. Syst. 23(10), 18719–18735 (2022). [Google Scholar]
- M.E. Khan, H. Rue, The Bayesian learning rule. J. Mach. Learn. Res. 24, 46 (2023). [Google Scholar]
- J.Y. Audibert, S. Bubeck, Minimax policies for adversarial and stochastic bandits. In Proc. Conf. Learn. Theory (COLT), Montreal, Canada, June 18–21, pp. 217–226 (2009). [Google Scholar]
- S. Bubeck, N. Cesa-Bianchi, Regret analysis of stochastic and nonstochastic multi- armed bandit problems. Found. Trends Mach. Learn. 5, 1–122 (2012). [Google Scholar]
- S. Agrawal, N. Goyal, Analysis of Thompson sampling for the multi-armed bandit problem. arXiv:1111.1797 (2011). [Google Scholar]
- P. Auer, Using confidence bounds for exploitation-exploration trade-offs. J. Mach. Learn. Res. 3, 397–422 (2002). [MathSciNet] [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.