Results 31 to 40 of about 2,781,483 (288)

Learning a Policy for Opportunistic Active Learning

, 2018
Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions.
Mooney, Raymond J., Padmakumar, Aishwarya, Stone, Peter   +2 more
core   +1 more source

A qualitative framework to learn from Failures: reducing risks and developing effective financial policies

European Journal of Islamic Finance, 2018
This article explores policy failures phenomena and makes suggestions to draw lessons from past mistakes in order to improve financial policies in the future.
Mustafa Mahmoud Hamed
doaj   +1 more source

Learning from Other Places and Their Plans: Comparative Learning in and for Planning Systems

Urban Planning, 2020
In this thematic issue we pursue the idea that comparative studies of planning systems are utterly useful for gaining a deeper understanding of learning processes and learning capacity in spatial planning systems.
Kristof Van Assche, Raoul Beunen, Stefan Verweij   +2 more
doaj   +1 more source

Learning multi-agent cooperation

Frontiers in Neurorobotics, 2022
Advances in reinforcement learning (RL) have resulted in recent breakthroughs in the application of artificial intelligence (AI) across many different domains.
Corban Rivera, Edward Staley, Ashley Llorens   +2 more
doaj   +1 more source

Distributed Algorithms for Learning and Cognitive Medium Access with Logarithmic Regret [PDF]

, 2010
The problem of distributed learning and channel access is considered in a cognitive network with multiple secondary users. The availability statistics of the channels are initially unknown to the secondary users and are estimated using sensing decisions.
Ananthram Swami, Animashree An, Ao Kevin Tang, Nithin Michael, Student Member   +4 more
core   +6 more sources

Real–Sim–Real Transfer for Real-World Robot Control Policy Learning with Deep Reinforcement Learning

Applied Sciences, 2020
Compared to traditional data-driven learning methods, recently developed deep reinforcement learning (DRL) approaches can be employed to train robot agents to obtain control policies with appealing performance. However, learning control policies for real-
Naijun Liu, Yinghao Cai, Tao Lu, Rui Wang, Shuo Wang   +4 more
doaj   +1 more source

From a Caring State to an Investing State. Stages of a Changing Welfare Model in Labour Market Policy

Central European Journal of Public Policy, 2021
In this paper, we investigate the changing model of social security. The analyses are focusing on changes in labour market policies which have taken place in the countries of the European Union.
Csoba Judit
doaj   +1 more source

Learning with Options that Terminate Off-Policy

, 2017
A temporally abstract action, or an option, is specified by a policy and a termination condition: the policy guides option behavior, and the termination condition roughly determines its length.
Bacon, Pierre-Luc, Harutyunyan, Anna, Nowe, Ann, Precup, Doina, Vrancx, Peter   +4 more
core   +1 more source

Anticipated Fiscal Policy and Adaptive Learning [PDF]

, 2007
We consider the impact of anticipated policy changes when agents form expectations using adaptive learning rather than rational expectations. To model this we assume that agents combine limited structural knowledge with a standard adaptive learning rule.
Evans, George W., Honkapohja, Seppo, Kaushik, Mitra   +2 more
core   +2 more sources

Learning from experience leading to engagement: for a Europe of religion and belief diversity [PDF]

, 2012
The Religious Diversity and Anti-Discrimination Training Program provides a remarkable opportunity for participants of all walks of life to share opinions, concerns and needs of a variety of very real and practical issues such as the role of religion in ...
Cheruvallil-Contractor, Sariya, Weller, Paul   +1 more
core   +1 more source