Results 21 to 30 of about 8,751,520 (309)

Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension [PDF]

open access: yesFindings, 2020
Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness against those adversarial attacks but hurts generalization of the models.
Adyasha Maharana, Mohit Bansal
semanticscholar   +1 more source

MPC-Net: A First Principles Guided Policy Search [PDF]

open access: yesIEEE Robotics and Automation Letters, 2019
We present an Imitation Learning approach for the control of dynamical systems with a known model. Our policy search method is guided by solutions from Model Predictive Control (MPC).
Jan Carius   +2 more
semanticscholar   +1 more source

A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials [PDF]

open access: yesIEEE Transactions on robotics, 2018
Most policy search (PS) algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only ...
Konstantinos Chatzilygeroudis   +4 more
semanticscholar   +1 more source

Policy implications for familial searching [PDF]

open access: yesInvestigative Genetics, 2011
Abstract In the United States, several states have made policy decisions regarding whether and how to use familial searching of the Combined DNA Index System (CODIS) database in criminal investigations. Familial searching pushes DNA typing beyond merely identifying individuals to detecting genetic relatedness, an application previously ...
Kim, Joyce   +3 more
openaire   +2 more sources

Quantum architecture search via truly proximal policy optimization

open access: yesScientific Reports, 2023
Quantum Architecture Search (QAS) is a process of voluntarily designing quantum circuit architectures using intelligent algorithms. Recently, Kuo et al. (Quantum architecture search via deep reinforcement learning.
Xianchao Zhu, Xiaokai Hou
doaj   +1 more source

Improving the Effectiveness and Efficiency of Web-Based Search Tasks for Policy Workers

open access: yesInformation, 2023
We adapt previous literature on search tasks for developing a domain-specific search engine that supports the search tasks of policy workers. To characterise the search tasks we conducted two rounds of interviews with policy workers at the municipality ...
Thomas Schoegje   +3 more
doaj   +1 more source

Learning Classical Planning Strategies with Policy Gradient [PDF]

open access: yes, 2019
A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process.
Alrajeh, Dalal   +2 more
core   +2 more sources

Directed search, unemployment and public policy [PDF]

open access: yesCanadian Journal of Economics/Revue canadienne d'économique, 2009
Abstract We examine the effects of public policy parameters in a simple directed search model of the labour market, and contrast them with those in standard random matching models with Nash bargaining. Both finite and limit versions of the directed search model are considered, and the value of the limit model as an approximation of the finite one is ...
Kennes, John   +3 more
openaire   +3 more sources

Expressive Attribute-based Searchable Encryption Scheme in Cloud Computing [PDF]

open access: yesJisuanji kexue, 2022
Searchable encryption technology can realize keyword search without decrypting the data,and thus well protects user'sprivate information.Aiming at the problem that most current searchable encryption schemes cannot support user-defined search strategies ...
GAO Shi-yao, CHEN Yan-li, XU Yu-lan
doaj   +1 more source

Black-box data-efficient policy search for robotics [PDF]

open access: yesIEEE/RJS International Conference on Intelligent RObots and Systems, 2017
The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a policy that ...
Konstantinos Chatzilygeroudis   +5 more
semanticscholar   +1 more source

Home - About - Disclaimer - Privacy