2022
DOI: 10.1016/j.clinthera.2021.11.002
|View full text |Cite
|
Sign up to set email alerts
|

Reinforcement Learning Methods in Public Health

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2
2

Relationship

0
9

Authors

Journals

citations
Cited by 15 publications
(6 citation statements)
references
References 66 publications
0
5
0
Order By: Relevance
“… 89 At the same time, in order to minimize the waste of nursing and medical resources, it has been argued that the precise implementation of care with known goals is an efficient and effective solution to avoid the waste of resources. 90 Therefore, there is a current need to identify the care needs of older adults with different disabilities and to achieve precise implementation in order to achieve the goal of optimizing care delivery. Our present study reveals the care services needed by the disabled elderly population.…”
Section: Discussionmentioning
confidence: 99%
“… 89 At the same time, in order to minimize the waste of nursing and medical resources, it has been argued that the precise implementation of care with known goals is an efficient and effective solution to avoid the waste of resources. 90 Therefore, there is a current need to identify the care needs of older adults with different disabilities and to achieve precise implementation in order to achieve the goal of optimizing care delivery. Our present study reveals the care services needed by the disabled elderly population.…”
Section: Discussionmentioning
confidence: 99%
“…The COVID-19 epidemic has spawned companies investing in public health 18 . Among the OECD countries, public health accounts for a significant share of Canada’s total healthcare costs.…”
Section: Methodsmentioning
confidence: 99%
“…Identify the Counterfactual Best. In settings where arm means are shifting over time, it is challenging to define the notion of a "bestarm" as the mean performance of an arm and the identity of the best arm may change daily [28]. To bridge this gap, our proposed objective is to identify with high probability the treatment that would have obtained the highest possible reward, if all traffic had been diverted to it.…”
Section: Lessons Learnedmentioning
confidence: 99%
“…This includes the famed EXP3 algorithm [19]. There is far less work on this in the pure exploration setting with the notable exception of [1] and a recent extension to linear bandits [28,29].…”
Section: Appendix a Related Workmentioning
confidence: 99%