Abstract
Pandemic influenza has the epidemiological potential to kill millions of people.
While different preventive measures exist, it remains challenging to implement them in an effective and efficient way.
To improve preventive strategies, it is necessary to thoroughly understand their impact on the complex dynamics of influenza epidemics. To this end, epidemiological models provide an essential tool to evaluate such strategies \textit{in silico}.
Epidemiological models are frequently used to assist the decision making concerning the mitigation of ongoing epidemics. Therefore, rapidly identifying the most promising preventive strategies is crucial to adequately inform public health officials.
To this end, we formulate the evaluation of prevention strategies as a multi-armed bandit problem. The utility of this novel evaluation method is validated through experiments in the context of an individual-based influenza model.
We demonstrate that it is possible to identify the optimal strategy using only a limited number of model evaluations, even if there is a large number of preventive strategies to consider.
While different preventive measures exist, it remains challenging to implement them in an effective and efficient way.
To improve preventive strategies, it is necessary to thoroughly understand their impact on the complex dynamics of influenza epidemics. To this end, epidemiological models provide an essential tool to evaluate such strategies \textit{in silico}.
Epidemiological models are frequently used to assist the decision making concerning the mitigation of ongoing epidemics. Therefore, rapidly identifying the most promising preventive strategies is crucial to adequately inform public health officials.
To this end, we formulate the evaluation of prevention strategies as a multi-armed bandit problem. The utility of this novel evaluation method is validated through experiments in the context of an individual-based influenza model.
We demonstrate that it is possible to identify the optimal strategy using only a limited number of model evaluations, even if there is a large number of preventive strategies to consider.
| Original language | English |
|---|---|
| Pages | 67-85 |
| Number of pages | 19 |
| DOIs | |
| Publication status | Published - 9 May 2017 |
| Event | 2017 Adaptive Learning Agents (ALA) workshop: Workshop of the AAMAS conference - World trade center, Sao Paolo, Brazil Duration: 8 May 2017 → 9 May 2017 http://ala2017.it.nuigalway.ie/ http://ala2017.it.nuigalway.ie |
Workshop
| Workshop | 2017 Adaptive Learning Agents (ALA) workshop |
|---|---|
| Abbreviated title | ALA-2017 |
| Country/Territory | Brazil |
| City | Sao Paolo |
| Period | 8/05/17 → 9/05/17 |
| Internet address |
Keywords
- Epidemiological models
- Multi-armed bandits
- Pandemic influenza
- Preventive strategies
- Reinforcement learning