Results 91 to 100 of about 122,392 (268)

A Q‐Learning Algorithm to Solve the Two‐Player Zero‐Sum Game Problem for Nonlinear Systems

International Journal of Adaptive Control and Signal Processing, Volume 39, Issue 3, Page 566-581, March 2025.
A Q‐learning algorithm to solve the two‐player zero‐sum game problem for nonlinear systems. ABSTRACT This paper deals with the two‐player zero‐sum game problem, which is a bounded L2$$ {L}_2 $$‐gain robust control problem. Finding an analytical solution to the complex Hamilton‐Jacobi‐Issacs (HJI) equation is a challenging task.
Afreen Islam, Anthony Siming Chen, Guido Herrmann   +2 more
wiley   +1 more source

Improving sample efficiency and exploration in upside-down reinforcement learning

Journal of Information and Intelligence
Supervised learning has been demonstrated to be a stable approach for training deep neural networks. Upside-down reinforcement learning solves reinforcement learning problems by using supervised learning, but this method suffers from weak sample ...
Mohammadreza Nakhaei, Reza Askari Moghadam   +1 more
doaj   +1 more source

Characterization of Defect Distribution in an Additively Manufactured AlSi10Mg as a Function of Processing Parameters and Correlations with Extreme Value Statistics

Advanced Engineering Materials, EarlyView.
Predicting extreme defects in additive manufacturing remains a key challenge limiting its structural reliability. This study proposes a statistical framework that integrates Extreme Value Theory with advanced process indicators to explore defect–process relationships and improve the estimation of critical defect sizes. The approach provides a basis for
Muhammad Muteeb Butt, Varma Kvvssn, Hossein Laieghi, Zia Uddin, Peyman Ansari, E. Kıvanç Sadak, Can Barış Toprak, Hüseyin Kızıl, Enrico Salvati   +8 more
wiley   +1 more source

Learning to Hint for Reinforcement Learning

CoRR
Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal.
Yu Xia 0007, Canwen Xu, Zhewei Yao, Julian J. McAuley, Yuxiong He   +4 more
openaire   +3 more sources

Delays in Reinforcement Learning

CoRR, 2023
Delays are inherent to most dynamical systems. Besides shifting the process in time, they can significantly affect their performance. For this reason, it is usually valuable to study the delay and account for it. Because they are dynamical systems, it is of no surprise that sequential decision-making problems such as Markov decision processes (MDP) can
openaire   +3 more sources

Thermodynamic Pathways of Nonequilibrium Solidification in Wire‐Arc Additive Manufacturing Fe‐Based Multicomponent Alloy Structures

Advanced Engineering Materials, EarlyView.
Geometry‐driven thermal behavior in wire‐arc additive manufacturing (WAAM) influences microstructural evolution during nonequilibrium solidification of a chemically complex Fe–Cr–Nb–W–Mo–C nanocomposite system. By comparing different deposits configurations, distinct entropy–cooling rate correlations, segregation, and carbide evolution are revealed ...
Blanca Palacios, Anthony Gonzalez, Aleksander Aleman, Tyler Dolmetsch, Tanaji Paul, Arvind Agarwal   +5 more
wiley   +1 more source

A Simplified Laminar Flow Model for the Pultrusion of Glass Fiber/Polyethylene Terephthalate Commingled Yarns

Advanced Engineering Materials, EarlyView.
A simplified thermoplastic pultrusion model is developed to predict thermal fields in glass fiber/polyethylene terephthalate (GF/PET) composites with reduced computational cost. By combining effective material homogenization, validation against literature data, and Gaussian‐process‐based optimization, the study reveals how heating limits, pulling speed,
Elder Soares, Nadège Bouchonneau, Christian Jochum, Donald Radford   +3 more
wiley   +1 more source

Adaptive Foam 3D Printing of Ultralight and Multifunctional Materials

Advanced Engineering Materials, EarlyView.
Adaptive foam 3D printing, enabled by expandable microspheres, imparts cellular structures to thermoplastic and thermosetting polymers, manufactured through a variety of processes including fused filament fabrication, direct ink writing, digital light processing, and inkjet printing.
Nariman Rajabifar, Amir Ameli
wiley   +1 more source

High‐Entropy Alloy Interlayers Toward Advanced Joining for High‐Performance Structural Applications: Current Progress and Emerging Challenges

Advanced Engineering Materials, EarlyView.
HEA interlayers offer a versatile route for joining high‐performance structural materials. Their compositional and structural design regulates interfacial reactions, suppresses brittle IMCs, and improves metallurgical bonding. Sandwich interlayers further integrate defect healing with precipitation strengthening, enabling improved strength–ductility ...
Lin Yuan, Jiafen Song, Jinglong Li, Jiangtao Xiong, Tao Yang   +4 more
wiley   +1 more source

Reinforcement learning-based energy management for hybrid electric vehicles: A comprehensive up-to-date review on methods, challenges, and research gaps

Energy and AI
Reinforcement learning is widely used for control applications and has also been successfully implemented for efficient energy management within hybrid electric vehicles.
Mohamed Nadir Boukoberine, Muhammad Fahad Zia, Tarek Berghout, Mohamed Benbouzid   +3 more
doaj   +1 more source