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...
Главный автор: | Treetanthiploet, T |
---|---|
Другие авторы: | Cohen, S |
Формат: | Диссертация |
Язык: | English |
Опубликовано: |
2021
|
Предметы: |
Схожие документы
-
Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
по: Dan Ben Ami, и др.
Опубликовано: (2025-01-01) -
An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits
по: Isaac J. Sledge, и др.
Опубликовано: (2018-02-01) -
Output-weighted sampling for multi-armed bandits with extreme payoffs
по: Yang, Yibo, и др.
Опубликовано: (2024) -
Risk-aware multi-armed bandit problem with application to portfolio selection
по: Xiaoguang Huo, и др.
Опубликовано: (2017-01-01) -
Multi-Armed Bandits in Brain-Computer Interfaces
по: Frida Heskebeck, и др.
Опубликовано: (2022-07-01)