Results 91 to 100 of about 298,347 (266)

Learning to Walk Via Deep Reinforcement Learning

Robotics: Science and Systems XV, 2019
RSS 2019, https://sites.google.com/view/minitaur-locomotion/
Haarnoja, Tuomas, Ha, Sehoon, Zhou, Aurick, Tan, Jie, Tucker, George, Levine, Sergey   +5 more
openaire   +2 more sources

The Cuttlebone Blueprint for Multifunctional Metamaterials: Design Taxonomy, Functional Decoupling, and Future Horizons

Advanced Functional Materials, EarlyView.
Cuttlebone‐inspired metamaterials exploit a septum‐wall architecture to achieve excellent mechanical and functional properties. This review classifies existing designs into direct biomimetic, honeycomb‐type, and strut‐type architectures, summarizes governing design principles, and presents a decoupled design framework for interpreting multiphysical ...
Xinwei Li, Zhendong Li
wiley   +1 more source

Deep Reinforcement Learning with Double Q-Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2016
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively.
van Hasselt, Hado, Guez, Arthur, Silver, David   +2 more
openaire   +2 more sources

From Bug to Feature: Harnessing Cross‐Sensitivity for Multiparametric Luminescence Sensing

Advanced Functional Materials, EarlyView.
Cross‐sensitivity in luminescence sensing is reframed from a limitation into a resource for multiparametric detection. Using ruby microspheres as a model system, cross‐sensitivity is quantitatively assessed and exploited through linear discriminant analysis, enabling simultaneous, correction‐free pressure and temperature sensing with a single ...
Nikita Panov, Liyan Ming, Stanislav Sinogeikin, Erving Ximendes, Daniel Jaque, Riccardo Marin   +5 more
wiley   +1 more source

A Comprehensive Study on Reinforcement Learning and Deep Reinforcement Learning Schemes

Sir Syed University Research Journal of Engineering and Technology
Reinforcement learning (RL) has emerged as a powerful tool for creating artificial intelligence systems (AIS) and solving problems which require sequential decision-making. Reinforcement learning has achieved some impressive achievements in recent years,
Muhammad Azhar, Mansoor Ahmed Khuhro, Muhammad Waqas, Umair Saeed, Mehar Khan Niazi   +4 more
doaj   +1 more source

Metal–Organic Frameworks for Gaseous Pollutant Management: From Capture to Neutralization and Reutilization

Advanced Functional Materials, EarlyView.
This review maps how MOFs can manage hazardous gases by combining adsorption, neutralization, and reutilization, enabling sustainable air‐pollution control. Covering chemical warfare agent simulants, SO2, NOx, NH3, H2S, and volatile organic compounds, it highlights structure‐guided strategies that boost selectivity, water tolerance, and cycling ...
Yuanmeng Tian, Zeyu Tao, Kaikai Ma, Xiaoliang Wang, Bo Yu, Yiu Wan Yip, Zhijie Chen, Jin Shang, Bin Fei   +8 more
wiley   +1 more source

The advancements and applications of deep reinforcement learning in Go [PDF]

ITM Web of Conferences
Combining Deep Learning's perceptual skills with Reinforcement Learning's decision-making abilities, Deep Reinforcement Learning (DRL) represents a significant breakthrough in Artificial Intelligence (AI).
Zheng Xutao
doaj   +1 more source

BACH, a Bayesian Optimization Protocol for Accurate Coarse‐Grained Parameterization of Organic Liquids

Advanced Functional Materials, EarlyView.
We present a fully automated Bayesian optimization (BO) protocol for the parameterization of nonbonded interactions in coarse‐grain CG force fields (BACH). Using experimental thermophysical data, we apply the protocol to a broad range of liquids, spanning linear, branched, and unsaturated hydrocarbons, esters, triglycerides, and water.
Janak Prabhu, Akhil Pratap Singh, Pablo Campomanes, Stefano Vanni   +3 more
wiley   +1 more source

Classifying Options for Deep Reinforcement Learning

, 2016
In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the ...
Arulkumaran, Kai, Bharath, Anil Anthony, Dilokthanakul, Nat, Shanahan, Murray   +3 more
core  

Engineering Strategies for Stable and Long‐Life Alkaline Zinc‐Based Flow Batteries

Advanced Functional Materials, EarlyView.
Alkaline zinc‐based flow batteries face persistent challenges from unstable zinc deposition, including dendrite growth, passivation, corrosion, and hydrogen evolution, which severely limit cycling stability. Current research addresses these issues through coordinated electrode structuring, electrolyte regulation, and membrane design to control zinc ...
Yuran Bai, Xiaoyu Huo, Xin Long, Enkang Fu, Xusong Gong, Lei Wei, Liang An   +6 more
wiley   +1 more source