Results 21 to 30 of about 2,781,483 (288)
Efficient Deep Reinforcement Learning via Adaptive Policy Transfer
, 2020 Transfer Learning (TL) has shown great potential to accelerate Reinforcement Learning (RL) by leveraging prior knowledge from past learned policies of relevant tasks. Existing transfer approaches either explicitly computes the similarity between tasks or
Cheng, Yingfeng +10 more
core +1 more source
Campbell Systematic Reviews, 2007 There is a lack of evidence about the efficacy of behavioural or cognitive‐behavioural training interventions for foster carers. The programmes are intended to assist foster carers in the management of the difficult behaviour of looked‐after children and
William Turner +2 more
doaj +1 more source
, 2020 This is the author accepted manuscript. The final version is available from SAGE Publications via the ISBN in this record ; Learning is a fascinating topic for political science. Whether we look at comparative politics, public policy, or governance, we find that all these three main fields of political science are concerned with learning – but in ...
Dunlop, CA, Radaelli, CM
openaire +2 more sources
Learning Replanning Policies With Direct Policy Search [PDF]
IEEE Robotics and Automation Letters, 2019 Direct policy search has been successful in learning challenging real-world robotic motor skills by learning open-loop movement primitives with high sample efficiency. These primitives can be generalized to different contexts with varying initial configurations and goals.
Florian Brandherm +3 more
openaire +3 more sources
Policy learning and policy evaluation
, 2023 Published online: 19 October 2023 The theory and practice of evaluation have often been inspired by the motivation to learn. We explain the conceptual and causal connections between evaluation and learning, addressing three questions: what is the content of learning that is expected from evaluations? How is learning created? And what is learning useful
Claire A. Dunlop, Claudio M. Radaelli
openaire +3 more sources
Learning modular policies for robotics [PDF]
Frontiers in Computational Neuroscience, 2014 A promising idea for scaling robot learning to more complex tasks is to use elemental behaviors as building blocks to compose more complex behavior. Ideally, such building blocks are used in combination with a learning algorithm that is able to learn to select, adapt, sequence and co-activate the building blocks.
Neumann, G. +4 more
openaire +6 more sources
Multi-Task Policy Search for Robotics [PDF]
, 2014 © 2014 IEEE.Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics.
Deisenroth, MP +3 more
core +1 more source
Welfare Benefits and Ethnic Minorities: Transfers from Australia to the United-Kingdom
Miranda: Revue Pluridisciplinaire du Monde Anglophone, 2014 With a quarter of its population born overseas, Australia has had to face the challenges commonly associated with the integration of minority groups in a singularly acute manner.
Sophie Koppe
doaj +1 more source
Policy learning and policy change: exploring possibilities on the Advocacy Coalition Framework
Revista de Administração Pública, 2020 This article aims to advance the discussion about the influence of knowledge and policy learning on policy change, taking the Advocacy Coalition Framework as reference. We propose unlinking the comprehension of learning through change in two perspectives.
Janaina Ma, Diego Mota Vieira
doaj +2 more sources
Learning Optimal Fair Policies
Proceedings of machine learning research, 2018 Systematic discriminatory biases present in our society influence the way data is collected and stored, the way variables are defined, and the way scientific findings are put into practice as policy. Automated decision procedures and learning algorithms applied to such data may serve to perpetuate existing injustice or unfairness in our society.
Nabi, Razieh +2 more
openaire +3 more sources