Results 101 to 110 of about 171,350 (313)

The Mean-Squared Error of Double Q-Learning [PDF]

arXiv, 2020
In this paper, we establish a theoretical comparison between the asymptotic mean-squared error of Double Q-learning and Q-learning. Our result builds upon an analysis for linear stochastic approximation based on Lyapunov equations and applies to both tabular setting and with linear function approximation, provided that the optimal policy is unique and ...
arxiv  

Electroplating of Wear‐ and Corrosion‐Resistant CrCoNi Medium‐Entropy Alloys beyond Hard Chromium Coatings

Advanced Functional Materials, EarlyView.
The electroplating of a CrCoNi medium‐entropy alloy is achieved using a mixture of an ionic liquid and an aqueous solution containing metal salts. The CrCoNi medium‐entropy alloy thin film exhibits high wear and corrosion resistance superior to conventional hard chromium coatings. Abstract High‐entropy alloys (HEAs) and medium‐entropy alloys (MEAs) are
Yuki Murakami, Shuhei Yoshida, Kosuke Ishii, Naoya Nishi, Akiyuki Ryoki, Nobuhiro Tsuji, Kuniaki Murase, Kazuhiro Fukami   +7 more
wiley   +1 more source

Reinforcement Learning-Based Autonomous Soccer Agents: A Study in Multi-Agent Coordination and Strategy Development

Buana Information Technology and Computer Sciences
Reinforcement learning (RL) approaches, particularly Q-learning, have emerged as strong tools for autonomous agent training, allowing agents to acquire optimum decision-making rules through interaction with their surroundings.
Biplov Paneru, Bishwash Paneru, Ramhari Poudyal, Khem Poudyal   +3 more
doaj   +1 more source

Ultra‐Fast Non‐Volatile Resistive Switching Devices with Over 512 Distinct and Stable Levels for Memory and Neuromorphic Computing

Advanced Functional Materials, EarlyView.
A materials and device design concept that comprises a self‐assembled ultra‐thin epitaxial ion‐transporting layer, an amorphous oxide overcoat oxygen‐blocking layer, and a partial filament formed during an electroforming step is proposed for low‐current multilevel resistive switching devices.
Ming Xiao, Markus Hellenbrand, Nives Strkalj, Babak Bakhit, Zhuotong Sun, Nikolaos Barmpatsalos, Dovydas Joksas, Hongyi Dou, Zedong Hu, Ping Lu, Samip Karki, Sundar Kunwar, Jonathan D. Major, Aiping Chen, Haiyan Wang, Quanxi Jia, Adnan Mehonic, Judith L. MacManus‐Driscoll   +17 more
wiley   +1 more source

Scheduling Bi-Objective Lot-Streaming Hybrid Flow Shops with Consistent Sublots via an Enhanced Artificial Bee Colony Algorithm

Complex System Modeling and Simulation
This work addresses bi-objective hybrid flow shop scheduling problems considering consistent sublots (Bi-HFSP_CS). The objectives are to minimize the makespan and total energy consumption.
Benxue Lu, Kaizhou Gao, Peiyong Duan, Adam Slowik   +3 more
doaj   +1 more source

Hierarchical clustering with deep Q-learning

Acta Universitatis Sapientiae, Informatica, 2018
Abstract Following up on our previous study on applying hierarchical clustering algorithms to high energy particle physics, this paper explores the possibilities to use deep learning to generate models capable of processing the clusterization themselves.
Forster, R., Fülöp, Ágnes
openaire   +6 more sources

Advances in Radiative Heat Transfer: Bridging Far‐Field Fundamentals and Emerging Near‐Field Innovations

Advanced Functional Materials, EarlyView.
This review synthesizes the evolution of radiative heat transfer, emphasizing the transition from far‐field to near‐field regimes. Traditional frameworks, such as Planck's law, are revisited alongside modern innovations like fluctuational electrodynamics. Applications span nanoscale thermal management, energy harvesting, and thermophotovoltaic systems.
Ambali Alade Odebowale, Andergachew Berhe, Rasheed T. Ogundare, Salah Abdo, Amer Abdulghani, Haroldo T. Hattori, Andrey E. Miroshnichenko   +6 more
wiley   +1 more source

Tin‐Based 2D/3D Perovskite Vertical Heterojunction for High‐Performance Synaptic Phototransistors

Advanced Functional Materials, EarlyView.
Phototransistors based on tin‐based 2D/3D perovskite heterostructures show an ultrahigh responsivity and detectivity at a low gate voltage across a broad wavelength region from ultraviolet to near‐infrared. The devices can replicate neuromorphic learning and remembering behaviors to light stimuli, in addition to electric depression and memory erasure ...
Hok‐Leung Loi, Tianyue Wang, Dapeng Liu, Jiupeng Cao, Jing Zhuang, Zeyu Zhao, Yang Xu, Mitch Guijun Li, Liang Li, Tianyou Zhai, Feng Yan   +10 more
wiley   +1 more source

Robot control using Q-Learning [PDF]

Scientific Bulletin of the ''Petru Maior" University of Tîrgu Mureș, 2012
This paper focuses on machine learning, where an agent learns how to solve a specific problem. The learning process will take place in a simulated environment, so the effectiveness can be measured without any potential damage to real the robot. QLearning
Szántó Zoltán
doaj  

Assessing the Potential of Classical Q-learning in General Game Playing [PDF]

arXiv, 2018
After the recent groundbreaking results of AlphaGo and AlphaZero, we have seen strong interests in deep reinforcement learning and artificial general intelligence (AGI) in game playing. However, deep learning is resource-intensive and the theory is not yet well developed.
arxiv