Stochastic control approach to the multi-armed bandit problems
<p>A multi-armed bandit is the simplest problem to study learning under uncertainty when decisions affect information. A standard approach to the multi-armed bandit often gives a heuristic construction of an algorithm and proves its regret bound. Following a constructive approach, it is often...
主要作者: | Treetanthiploet, T |
---|---|
其他作者: | Cohen, S |
格式: | Thesis |
语言: | English |
出版: |
2021
|
主题: |
相似书籍
-
Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
由: Dan Ben Ami, et al.
出版: (2025-01-01) -
An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits
由: Isaac J. Sledge, et al.
出版: (2018-02-01) -
Output-weighted sampling for multi-armed bandits with extreme payoffs
由: Yang, Yibo, et al.
出版: (2024) -
Risk-aware multi-armed bandit problem with application to portfolio selection
由: Xiaoguang Huo, et al.
出版: (2017-01-01) -
Multi-Armed Bandits in Brain-Computer Interfaces
由: Frida Heskebeck, et al.
出版: (2022-07-01)