Results 91 to 100 of about 171,350 (313)

Smart Rubber Extrusion Line Combining Multiple Sensor Techniques for AI‐Based Process Control

Advanced Engineering Materials, EarlyView.
This publication presents a digitalization approach for a laboratory rubber extrusion line, employing innovative measurement methods and artificial intelligence (AI)‐based process control. The results demonstrate that the measurement systems are capable of detecting changes in the process and extrudate quality.
Alexander Aschemann, Paul‐Felix Hagen, Simon Albers, Robin Rofallski, Sven Schwabe, Mohammed Dagher, Marco Lukas, Sebastian Leineweber, Benjamin Klie, Patrick Schneider, Hagen Bossemeyer, Lennart Hinz, Markus Kästner, Birger Reitz, Eduard Reithmeier, Thomas Luhmann, Hainer Wackerbarth, Ludger Overmeyer, Ulrich Giese   +18 more
wiley   +1 more source

A Generalization Error for Q-Learning. [PDF]

Journal of machine learning research : JMLR, 2005
Planning problems that involve learning a policy from a single training set of finite horizon trajectories arise in both social science and medical fields. We consider Q-learning with function approximation for this setting and derive an upper bound on the generalization error.
openaire   +2 more sources

Combining Structured Data with Domain Knowledge in Battery Materials Research: The Case of Conductive Networks

Advanced Engineering Materials, EarlyView.
The combination of battery product and characterization ontology (BPCO) and domain knowledge guides hypotheses development and leads to new insights into material–property relationship of battery materials. The use of “intermediate data” is introduced as a concept, and examples are shown on its use to analyze the agglomeration of carbon black and its ...
Lisa Beran, Tobias Valentin Knapp, Albenc Nexha, Makara Lay, Bart‐Jan Niebuur, Tobias Kraus   +5 more
wiley   +1 more source

Advances in Hybrid Icing and Frosting Protection Strategies for Optics, Lens, and Photonics in Cold Environments Using Thin‐Film Acoustic Waves

Advanced Engineering Materials, EarlyView.
This article provides a comprehensive overview of fundamentals and recent advances of transparent thin‐film surface acoustic wave technologies on glass substrates for monitoring and prevention/elimination of fog, ice, and frost. Fogging, icing, or frosting on optical lenses, optics/photonics, windshields, vehicle/airplane windows, and solar panel ...
Hui Ling Ong, Zhangbin Ji, Luke Haworth, Yihao Guo, Jaime del Moral, Stefan Jacob, Ana Borras, Agustin R. Gonzalez‐Elipe, Jikai Zhang, Jian Zhou, Glen McHale, Yong‐Qing Fu   +11 more
wiley   +1 more source

Improved Dynamic Q-Learning Algorithm to Solve the Lot-Streaming Flowshop Scheduling Problem with Equal-Size Sublots

Complex System Modeling and Simulation
The lot-streaming flowshop scheduling problem with equal-size sublots (ELFSP) is a significant extension of the classic flowshop scheduling problem, focusing on optimize makespan.
Ping Wang, Renato De Leone, Hongyan Sang
doaj   +1 more source

Internal Temperature Evolution Metrology and Analytics in Li‐Ion Cells

Advanced Functional Materials, EarlyView.
This study investigates the non‐linear evolution of internal temperatures across diverse operating conditions, highlighting the disparities between internal and external measurements and the resulting thermal asymmetries. The coupled thermo‐electrochemical modeling framework provides a comprehensive analysis of various heat generation modes, examining ...
Anuththara S. J. Alujjage, Bairav S. Vishnugopi, Avijit Karmakar, David P. Magee, Yevgen Barsukov, Partha P. Mukherjee   +5 more
wiley   +1 more source

An autoscalable approach to optimize energy consumption using smart meters data in serverless computing

Science and Technology for Energy Transition
Serverless computing has evolved as a prominent paradigm within cloud computing, providing on-demand resource provisioning and capabilities crucial to Science and Technology for Energy Transition (STET) applications.
Kaur Jasmine, Chana Inderveer, Bala Anju
doaj   +1 more source

Q-Learning with Differential Entropy of Q-Tables [PDF]

arXiv, 2020
It is well-known that information loss can occur in the classic and simple Q-learning algorithm. Entropy-based policy search methods were introduced to replace Q-learning and to design algorithms that are more robust against information loss. We conjecture that the reduction in performance during prolonged training sessions of Q-learning is caused by a
arxiv  

Recent Advances in Single‐Atom Catalyst for Solar Energy Conversion: A Comprehensive Review and Future Outlook

Advanced Functional Materials, EarlyView.
This review highlights the potential of single‐atom catalysts in three key photocatalytic reactions: the hydrogen evolution reaction (HER), nitrogen reduction reaction for ammonia synthesis, and carbon dioxide reduction reaction (CO2RR) for chemical fuels.
Saad Mehmood, Saddam Sk, B. Moses Abraham, Mohsen Ahmadipour, Ujjwal Pal, Joydeep Dutta   +5 more
wiley   +1 more source

MinMaxMin $Q$-learning

MinMaxMin $Q$-learning is a novel optimistic Actor-Critic algorithm that addresses the problem of overestimation bias ($Q$-estimations are overestimating the real $Q$-values) inherent in conservative RL algorithms. Its core formula relies on the disagreement among $Q$-networks in the form of the min-batch MaxMin $Q$-networks distance which is added to ...
Soffair, Nitsan, Mannor, Shie
openaire   +2 more sources