Paper that introduced the PPO algorithm. PPO is, in a way, a response to the TRPO algorithm, trying to use the core idea but implement a more efficient and simpler algorithm.

TRPO defines the problem as a straight optimization problem, no learning is actually involved.

Tom Schaul, John Quan, Ioannis Antonoglou and David Silver. "PRIORITIZED EXPERIENCE REPLAY", ICLR, 2016.

Teodorescu, K., Plonsky, O., Ayal, S., & Barkan, R. (2021). Enforcement policies: Frequency of inspection is more important than the severity of punishment. PsyArXiv. https://doi.org/10.31234/osf.io/pbvzr

Claudia Sahm. (2022, January 5). “We, as experts, have a responsibility to policymakers and everyday people to match the strength of our recommendations to the strength of our data. When I read Oster, I see a tone and conviction that far exceeds the many limitations of her data.” https://t.co/NqWwj0hi28 [Tweet]. @Claudia_Sahm. https://twitter.com/Claudia_Sahm/status/1478532000441151488

Portfolio, B. and S. S. at N. (2021, November 3). No evidence school closures reduce the spread of COVID-19. Behavioural and Social Sciences at Nature Portfolio. http://socialsciences.nature.com/posts/no-evidence-school-closures-reduce-the-spread-of-covid-19

Chadi, M.-A., & Mousannif, H. (2021). Reinforcement Learning Based Decision Support Tool For Epidemic Control [Preprint]. PsyArXiv. https://doi.org/10.31234/osf.io/tcr8s

Moya, C., Cruz y Celis Peniche, P. D., Kline, M. A., & Smaldino, P. (2020). Dynamics of Behavior Change in the COVID World [Preprint]. SocArXiv. https://doi.org/10.31235/osf.io/kxajh

Bacher-Hicks, A., Goodman, J., & Mulhern, C. (2020). Inequality in Household Adaptation to Schooling Shocks: Covid-Induced Online Learning Engagement in Real Time (Working Paper No. 27555; Working Paper Series). National Bureau of Economic Research. https://doi.org/10.3386/w27555

Work That Can Be Done from Home: Evidence on Variation within and across Occupations and Industries. COVID-19 and the Labor Market. (n.d.). IZA – Institute of Labor Economics. Retrieved August 4, 2020, from https://covid-19.iza.org/publications/dp13374/

Jena, P. K. (2020). Impact of Covid-19 on Higher Education in India [Preprint]. SocArXiv. https://doi.org/10.31235/osf.io/jg8fr

‘It’s just way too much to take on’: School systems struggle with the politics of reopening. (n.d.). POLITICO. Retrieved June 28, 2020, from https://www.politico.com/news/2020/06/17/reopening-schools-coronavirus-327020

Latour, B. (2020 March 29). A little exercise to make sure that, after the virus crisis, things don't start again as they were before. Bruno-latour.fr. http://www.bruno-latour.fr/node/852.html

DELVE group publishes evidence paper on the use of face masks in tackling Coronavirus (COVID-19) pandemic | Royal Society. (2020 May 04). https://royalsociety.org/news/2020/05/delve-group-publishes-evidence-paper-on-use-of-face-masks/

Rahman, M. (2020, June 1). COVID-19 Public Sentiment Insights and Machine Learning for Tweets Classification. https://doi.org/10.31234/osf.io/sw2dn

Schwalbe, N., & Wahl, B. (2020). Artificial intelligence and the future of global health. The Lancet, 395(10236), 1579–1586. https://doi.org/10.1016/S0140-6736(20)30226-9

Barnby, J. M., Bell, V., Mehta, M., & Moutoussis, M. (2020, April 17). Reduction in social learning and policy uncertainty about intentional social threat underlies paranoia: evidence from modelling a modified serial dictator game. https://doi.org/10.31234/osf.io/jvx5y

Given that the article is framed as being about policy diffusion and using a policy learning framework, I would have expected more details here.

The NMHE website is about providing academic, financial and policies to new mexico public higher education institutions and community.

policy change index - machine learning on corpus of text to identify and predict policy changes in China

策略学习也是对话过程很重要的一环。 最近的策略学习过程有用基于有监督的预训练然后线上强化学习再训练的来提高学习的方案。但是这种方案有个潜在的毛病，在离线的数据中受限于数据量，线上一旦碰到了不常见的情况，容易直接恢复不来。(这个问题应该只是推断吧？有什么实证么？)

所以本文其实想说的是用一种方法来减轻线上和离线的差距。