Results 111 to 120 of about 685,298 (326)

Modern Deep Reinforcement Learning Algorithms [PDF]

arXiv, 2019
Recent advances in Reinforcement Learning, grounded on combining classical theoretical results with Deep Learning paradigm, led to breakthroughs in many artificial intelligence tasks and gave birth to Deep Reinforcement Learning (DRL) as a field of research. In this work latest DRL algorithms are reviewed with a focus on their theoretical justification,
arxiv  

Self‐organized Criticality in Neuromorphic Nanowire Networks With Tunable and Local Dynamics

Advanced Functional Materials, EarlyView.
Memristive nanowire networks (NWNs) are shown to be electrically tunable to a critical state where specific local dynamics evaluated by multiterminal characterization are exploited as feature selection in nonlinear transformation (NLT) tasks.
Fabio Michieletti, Davide Pilati, Gianluca Milano, Carlo Ricciardi   +3 more
wiley   +1 more source

A Nesterov's Accelerated quasi-Newton method for Global Routing using Deep Reinforcement Learning [PDF]

arXiv, 2020
Deep Q-learning method is one of the most popularly used deep reinforcement learning algorithms which uses deep neural networks to approximate the estimation of the action-value function. Training of the deep Q-network (DQN) is usually restricted to first order gradient based methods. This paper attempts to accelerate the training of deep Q-networks by
arxiv  

Active Learning‐Driven Discovery of Sub‐2 Nm High‐Entropy Nanocatalysts for Alkaline Water Splitting

Advanced Functional Materials, EarlyView.
High‐entropy nanoparticles (HENPs) hold great promise for electrocatalysis, yet optimizing their compositions remains challenging. This study employs active learning and Bayesian Optimization to accelerate the discovery of octonary HENPs for hydrogen and oxygen evolution reactions.
Sakthivel Perumal, Da Bean Han, Thandapani Marimuthu, Taewaen Lim, Hyun Woo Kim, Junhyeok Seo   +5 more
wiley   +1 more source

Pattern-Aware Intelligent Anti-Jamming Communication: A Sequential Deep Reinforcement Learning Approach

IEEE Access, 2019
This paper investigates the problem of anti-jamming communication in dynamic and intelligent jamming environment. A sequential deep reinforcement learning algorithm (SDRLA) without prior information is proposed, and raw spectrum information is used as ...
Songyi Liu, Yifan Xu, Xueqiang Chen, Ximing Wang, Meng Wang, Wen Li, Yangyang Li, Yuhua Xu   +7 more
doaj   +1 more source

Applications of Deep Reinforcement Learning in Communications and Networking: A Survey [PDF]

arXiv, 2018
This paper presents a comprehensive literature review on applications of deep reinforcement learning in communications and networking. Modern networks, e.g., Internet of Things (IoT) and Unmanned Aerial Vehicle (UAV) networks, become more decentralized and autonomous.
arxiv  

3D (Bio) Printing Combined Fiber Fabrication Methods for Tissue Engineering Applications: Possibilities and Limitations

Advanced Functional Materials, EarlyView.
Biofabrication aims at providing innovative technologies and tools for the fabrication of tissue‐like constructs for tissue engineering and regenerative medicine applications. By integrating multiple biofabrication technologies, such as 3D (bio) printing with fiber fabrication methods, it would be more realistic to reconstruct native tissue's ...
Waseem Kitana, Indra Apsite, Leonid Ionov   +2 more
wiley   +1 more source

A new approach for drone tracking with drone using Proximal Policy Optimization based distributed deep reinforcement learning

SoftwareX, 2023
In this paper, a distributed deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) is proposed for an unmanned aerial vehicle (UAV) to autonomously track another UAV. Accordingly, this paper makes three important contributions
Ziya Tan, Mehmet Karaköse
doaj  

An Invitation to Deep Reinforcement Learning

Foundations and Trends® in Optimization
Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is differentiable. For many interesting problems, this is however not the case.
Jaeger, Bernhard, Geiger, Andreas
openaire   +2 more sources

Integration of Perovskite/Low‐Dimensional Material Heterostructures for Optoelectronics and Artificial Visual Systems

Advanced Functional Materials, EarlyView.
Heterojunctions combining halide perovskites with low‐dimensional materials enhance optoelectronic devices by enabling precise charge control and improving efficiency, stability, and speed. These synergies advance flexible electronics, wearable sensors, and neuromorphic computing, mimicking biological vision for real‐time image analysis and intelligent
Yu‐Jin Du, Junjie Yang, Ziyu Lv, Yongbiao Zhai, Zezhuang Yi, Yuhui Xie, Ming‐Lin Zheng, Xiangyu Ma, Guodong Gong, Yan Wang, Ye Zhou, Su‐Ting Han   +11 more
wiley   +1 more source