Results 1 to 10 of about 1,717,828 (345)
, 2017 Recent advances in combining deep learning and Reinforcement Learning have shown a promising path for designing new control agents that can learn optimal policies for challenging control tasks.
Givargis, Tony, Mirzaei, Hamid
core +1 more source
External Prestressing Bridge Reinforcement Technology Review
MATEC Web of Conferences, 2015 Externally prestressed bridge can not only limit and reduce the cracks and deformation of the structure, improve the rigidity and bearing capacity of structure, improve the stress state of structure, but also have less interference for bridge operation ...
Zhu Hanbing, Yang Yaxun, Fan Weiya
doaj +1 more source
Deep Ordinal Reinforcement Learning
, 2019 Reinforcement learning usually makes use of numerical rewards, which have nice properties but also come with drawbacks and difficulties. Using rewards on an ordinal scale (ordinal rewards) is an alternative to numerical rewards that has received more ...
C Wirth, CJ Watkins, RS Sutton, V Mnih
core +1 more source
Suboptimal Choice Behaviour across Different Reinforcement Probabilities [PDF]
, 2015 Six adult roosters’ choice behaviour was investigated across a series of five experimental conditions and a series of replication of the same five experimental conditions. Stagner and Zentall (2010) found that pigeons prefer to choose an alternative with
Yang, Le
core +1 more source
On the speed of once-reinforced biased random walk on trees
, 2018 We study the asymptotic behaviour of once-reinforced biased random walk (ORbRW) on Galton-Watson trees. Here the underlying (unreinforced) random walk has a bias towards or away from the root.
Collevecchio, Andrea +2 more
core +1 more source
SensorsFish species’ biological vocalizations serve as essential acoustic signatures for passive acoustic monitoring (PAM) and ecological assessments. However, limited availability of high-quality acoustic recordings, particularly for region-specific species ...
Sunhyo Kim +7 more
doaj +1 more source
Action selection in modular reinforcement learning [PDF]
, 2014 textModular reinforcement learning is an approach to resolve the curse of dimensionality problem in traditional reinforcement learning. We design and implement a modular reinforcement learning algorithm, which is based on three major components: Markov ...
Zhang, Ruohan
core
The recycling of OMC's carbon reinforcement by solvolysing thermoset matrix. A way of sustainability for composites. [PDF]
, 2014 Originally developed for high-tech applications, carbon fibre/thermoset matrix composites have been increasingly used in leisure and sports industries, for several years.
AYMONIER, Cyril +5 more
core +3 more sources
SIAM Journal on Scientific ComputingInverse wave scattering aims at determining the properties of an object using data on how the object scatters incoming waves. In order to collect information, sensors are put in different locations to send and receive waves from each other. The choice of sensor positions and incident wave frequencies determines the reconstruction quality of scatterer ...
Hanyang Jiang, Yuehaw Khoo, Haizhao Yang
openaire +3 more sources
Applied SciencesGrouted sleeve connections are widely employed in the substructures of prefabricated bridges. After installation, the grout filling condition inside the sleeves cannot be directly inspected, while grouting defects may significantly compromise the ...
Anfan Shang +4 more
doaj +1 more source