Results 81 to 90 of about 171,350 (313)
A Reinforcement Learning Approach for Smart Farming [PDF]
Database Systems Journal, 2019 At a basic level, the aim of machine learning is to develop solutions for real-life engineering problems and to enhance the performance of different computers tasks in order to obtain an algorithm that is highly independent of human intervention.
Gabriela ENE
doaj
Decorrelated Double Q-learning [PDF]
arXiv, 2020 Q-learning with value function approximation may have the poor performance because of overestimation bias and imprecise estimate. Specifically, overestimation bias is from the maximum operator over noise estimate, which is exaggerated using the estimate of a subsequent state.
arxiv
International Journal of Adaptive Control and Signal Processing, EarlyView.Summary Data‐driven forecasting of ship motions in waves is investigated through feedforward and recurrent neural networks as well as dynamic mode decomposition. The goal is to predict future ship motion variables based on past data collected on the field, using equation‐free approaches.
Matteo Diez +2 more
wiley +1 more source
Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View [PDF]
arXiv, 2022 Q-learning has long been one of the most popular reinforcement learning algorithms, and theoretical analysis of Q-learning has been an active research topic for decades. Although researches on asymptotic convergence analysis of Q-learning have a long tradition, non-asymptotic convergence has only recently come under active study.
arxiv
Active deep Q-learning with demonstration [PDF]
Machine Learning, 2019 Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice.
Si-An Chen +3 more
openaire +4 more sources
International Journal of Adaptive Control and Signal Processing, EarlyView.The cost as a function of the number of experiments for a non‐symmetric 21×21$$ 21\times 21 $$ system. Four approaches are shown: the proposed stochastic conjugate gradient ILC (SCGILC) method (), deterministic conjugate gradient ILC (), stochastic gradient descent ILC () and deterministic gradient descent ILC ().
Leontine Aarnoudse, Tom Oomen
wiley +1 more source
IEEE Access, 2019 Energy and economy are increasing the relationship over the years, where the energy becomes a significant resource to keep a country developing, and it supports its economy.
Lucas Roberto Ferreira +2 more
doaj +1 more source
Advanced Engineering Materials, EarlyView.In this study, OpenPhase software is used to simulate low‐carbon bainitic steels. The lower holding temperature sample exhibits smaller and finer grains. Grain thickness measurements of bainitic ferrite from simulations align with the experimental observations at high temperature. Bainitic steels are extensively utilized across various sectors, such as
Dhanunjaya K. Nerella +7 more
wiley +1 more source
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning
Sensors, 2019 The maximum power point tracking (MPPT) technique is often used in photovoltaic (PV) systems to extract the maximum power in various environmental conditions.
Kuan-Yu Chou +2 more
doaj +1 more source