More Like this

1. Modular Policy Composition with Policy Centroids

   Adhikaray, Sandesh ; Boots, Byron ( April 2022 , The Multi-disciplinary Conference on Reinforcement Learning and Decision Making)
2. Statistically Efficient Off-Policy Policy Gradients

   Kallus, Nathan ; Uehara, Masatoshi ( January 2020 , International Conference on Machine Learning)
3. Representation Balancing MDPsfor Off-Policy Policy Evaluation

   Liu, Y ; Gottesman, O ; Raghu, A ; Komorowski, M ; Faisal, A ; Doshi-Velez, F ; Brunskill, E ( January 2018 , Advances in neural information processing systems)
4. Policy Expansion in Local Government Environmental Policy Making

   https://doi.org/10.1111/puar.12905  

   Arnold, Gwen ; Long, Le Anh Nguyen ( January 2018 , Public Administration Review)

   Relatively little is known about when, why, and how some jurisdictions “double down” on policy priorities, rapidly adopting multiple measures tackling the same issue. Rapid policy expansion can emerge in fast‐evolving, uncertain, and contested policy arenas in which pressures for policy making are not satisfied, and even may be strengthened, by initial policy innovation. This article analyzes local government policy making on high‐volume hydraulic fracturing by New York State municipalities from 2008 to 2012. Policy path dependence, peer influence, and policy design appear to play a critical role in determining whether public officials respond to these pressures with policy expansion. Initial policy innovations can open windows for policy participants to secure additional measures that strengthen or enlarge the scope of action. Public officials and stakeholders seeking particular policy outcomes should take a long view of the policy process while simultaneously remaining alert for opportunities afforded by pressurized policy dilemmas.

    

   more » « less
5. Data-Efficient Policy Evaluation Through Behavior Policy Search

   Hanna, J ; Thomas, P ; Stone, P ; Niekum, S ( August 2017 , International Conference on Machine Learning)