Now showing items 1-10 of 362
A fast hybrid reinforcement learning framework with human corrective feedback
Reinforcement Learning agents can be supported by feedback from human teachers in the learning loop that guides the learning process. In this work we propose two hybrid strategies of Policy Search Reinforcement Learning ...
An Interactive Framework for Learning Continuous Actions Policies Based on Corrective Feedback
(Springer Netherlands, 2019)
© 2018, Springer Science+Business Media B.V., part of Springer Nature.The main goal of this article is to present COACH (COrrective Advice Communicated by Humans), a new learning framework that allows non-expert humans to ...
Aprendizaje de políticas públicas. El caso del Instituto Coahuilense de Acceso a la Información Pública en México
(Facultad de Finanzas, Gobierno y Relaciones Internacionales, 2019-06-17)
El objetivo del presente artículo es proponer un modelo para el análisis empírico del aprendizaje generado en las políticas públicas. El modelo fue aplicado en el Instituto Coahuilense de Acceso a la Información Pública ...
The choice of innovation policy instruments
(Elsevier Inc., 2016)
ICT & learning in Chilean schools: Lessons learned
(PERGAMON-ELSEVIER SCIENCE LTD, 2008-12)
By the early nineties a Chilean network on computers and education for public schools had emerged. There were both high expectancies that technology could revolutionize education as well as divergent voices that doubted ...
A random walk through the trees: Forecasting copper prices using decision learning methods
We investigate the accuracy of copper price forecasts produced by three decision learning methods. Prior evidence (Liu et al. Resources Policy, 2017) shows that a regression tree, a simple decision learning model, can be ...
Sequential interdiction with incomplete information and learning
(INFORMS Inst.for Operations Res.and the Management Sciences, 2019)
© 2019 INFORM. We present a framework for a class of sequential decision-making problems in the context of general interdiction problems, in which a leader and a follower repeatedly interact. At each period, the leader ...
Smart food policies for obesity prevention
Prevention of obesity requires policies that work. In this Series paper, we propose a new way to understand how food policies could be made to work more effectively for obesity prevention. Our approach draws on evidence ...
Resilience for disaster risk management in a changing climate: Practitioners’ frames and practices
There is a growing use of resilience ideas within the disaster risk management literature and policy domain. However, few empirical studies have focused on how resilience ideas are conceptualized by practitioners, as ...