Adaptive policies for use of physical distancing interventions during the COVID-19 pandemic

Yaesoubi, Reza; Havumaki, Joshua; Chitwood, Melanie H.; Menzies, Nicolas A; Gonsalves, Gregg; Salomon, Joshua A.; Paltiel, A. David; Cohen, Ted

doi:10.1101/2020.05.29.20065714

Cited by 2 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several recent contributions have proposed such implementations. Yaesoubi et al (2020) applied an approximate policy iteration algorithm of their own (Yaesoubi & Cohen, 2016) on a seir model calibrated on the 1918 Influenza Pandemic in San Francisco. An interesting contribution of the paper was the development of a pragmatic decision tool to characterize adaptive policies that combined real-time surveillance data with clear decision rules to guide when to trigger, continue, or stop physical distancing interventions.…”

Section: Discussionmentioning

confidence: 99%

“…(Kompella et al, 2020) applied the Soft-Actor-Critic algorithm (Haarnoja et al, 2018) on an agent-based epidemiological model with community interactions allowing the spread of the disease to be an emergent property of people's behaviors and the government's policies. Other contributions applied non-rl optimization methods such as deterministic rules (Tarrataca et al, 2020), stochastic approximation algorithms (Yaesoubi et al, 2020), optimal control (Charpentier et al, 2020) or Bayesian optimization (Chandak et al, 2020). This latter paper also proposes a stochastic agent-based model called VIPER (Virus-Individual-Policy-EnviRonment) allowing to compare the optimization results on variations of the demographics and geographical distribution of population.…”

Section: Discussionmentioning

confidence: 99%

“…These contributions mostly differ by their definition of epidemiological models (e.g. seir: Yaesoubi et al, 2020, agent-based models: Chandak et al, 2020 or a combination of both: Kompella et al, 2020), of optimization methods (e.g. deterministic rules: Tarrataca et al, 2020, Bayesian optimization: Chandak et al, 2020, Deep rl: Arango & Pelov, 2020Kompella et al, 2020, optimal control: Charpentier et al, 2020, evolutionary optimization: Miikkulainen et al, 2020 or game-theoretic analysis: Elie et al, 2020), of cost functions (e.g.…”

Section: Related Workmentioning

confidence: 99%

“…fixed weighted sum of health and economic costs: Arango & Pelov, 2020;Kompella et al, 2020, possibly adding constraints on the school closure budget: Libin et al, 2020, or multi-objective optimization: Miikkulainen et al, 2020, of state and action spaces (e.g. using the entire observed epidemic history: Yaesoubi et al, 2020 or an im-…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

Colas¹,

Hejblum²,

Rouillon³

et al. 2021

jair

View full text Add to dashboard Cite

Modeling the dynamics of epidemics helps to propose control strategies based on pharmaceuticaland non-pharmaceutical interventions (contact limitation, lockdown, vaccination,etc). Hand-designing such strategies is not trivial because of the number of possibleinterventions and the difficulty to predict long-term effects. This task can be cast as an optimization problem where state-of-the-art machine learning methods such as deep reinforcement learning might bring significant value. However, the specificity of each domain|epidemic modeling or solving optimization problems|requires strong collaborationsbetween researchers from different fields of expertise. This is why we introduce EpidemiOptim, a Python toolbox that facilitates collaborations between researchers inepidemiology and optimization. EpidemiOptim turns epidemiological models and cost functions into optimization problems via a standard interface commonly used by optimization practitioners (OpenAI Gym). Reinforcement learning algorithms based on QLearning with deep neural networks (DQN) and evolutionary algorithms (NSGA-II) are already implemented. We illustrate the use of EpidemiOptim to find optimal policies fordynamical on-o lockdown control under the optimization of the death toll and economic recess using a Susceptible-Exposed-Infectious-Removed (SEIR) model for COVID-19. Using EpidemiOptim and its interactive visualization platform in Jupyter notebooks, epidemiologists, optimization practitioners and others (e.g. economists) can easily compare epidemiological models, costs functions and optimization algorithms to address important choicesto be made by health decision-makers. Trained models can be explored by experts and non-experts via a web interface. This article is part of the special track on AI and COVID-19.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

Colas¹,

Hejblum²,

Rouillon³

et al. 2021

jair

View full text Add to dashboard Cite

show abstract

“…These contributions mostly differ by their definition of epidemiological models (e.g. SEIR (Yaesoubi et al, 2020) or agent-based models (Chandak et al, 2020)), of optimization methods (e.g. deterministic rules (Tarrataca et al, 2020), Bayesian optimization (Chandak et al, 2020), Deep RL (Arango & Pelov, 2020) or evolutionary optimization (Miikkulainen et al, 2020)), of cost functions (e.g.…”

Section: Introductionmentioning

confidence: 99%

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

Colas¹,

Hejblum²,

Rouillon³

et al. 2020

Preprint

View full text Add to dashboard Cite

Epidemiologists model the dynamics of epidemics in order to propose control strategies based on pharmaceutical and non-pharmaceutical interventions (contact limitation, lock down, vaccination, etc). Hand-designing such strategies is not trivial because of the number of possible interventions and the difficulty to predict long-term effects. This task can be cast as an optimization problem where state-of-the-art machine learning algorithms such as deep reinforcement learning, might bring significant value. However, the specificity of each domainepidemic modelling or solving optimization problem -requires strong collaborations between researchers from different fields of expertise. This is why we introduce EpidemiOptim, a Python toolbox that facilitates collaborations between researchers in epidemiology and optimization. EpidemiOptim turns epidemiological models and cost functions into optimization problems via a standard interface commonly used by optimization practitioners (OpenAI Gym). Reinforcement learning algorithms based on Q-Learning with deep neural networks (DQN) and evolutionary algorithms (NSGA-II) are already implemented. We illustrate the use of EpidemiOptim to find optimal policies for dynamical on-off lock-down control under the optimization of death toll and economic recess using a Susceptible-Exposed-Infectious-Removed (SEIR) model for COVID-19. Using EpidemiOptim and its interactive visualization platform in Jupyter notebooks, epidemiologists, optimization practitioners and others (e.g. economists) can easily compare epidemiological models, costs functions and optimization algorithms to address important choices to be made by health decision-makers.

show abstract

Adaptive policies for use of physical distancing interventions during the COVID-19 pandemic

Cited by 2 publications

References 10 publications

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models

Contact Info

Product

Resources

About