Filters








11,961 Hits in 4.3 sec

Deep Reinforcement Learning with Sarsa and Q-Learning: A Hybrid Approach

Zhi-xiong XU, Lei CAO, Xi-liang CHEN, Chen-xi LI, Yong-liang ZHANG, Jun LAI
2018 IEICE transactions on information and systems  
In this paper, we present the Deep Sarsa and Q Networks (DSQN) algorithm, which can considered as an enhancement to the Deep Q Networks algorithm.  ...  Especially, we introduce Sarsa learning to Deep Q Networks for removing overestimations further.  ...  Acknowledgments This work was supported by the National Natural Science Fund Projects (61203192), and was also supported by the Natural Science Fund Project in Jiangsu province (BK2011124).  ... 
doi:10.1587/transinf.2017edp7278 fatcat:54n4digi3bgcvodb2rw6xob2ii

Power Allocation in Cache-Aided NOMA Systems: Optimization and Deep Reinforcement Learning Approaches [article]

Khai Nguyen Doan, Mojtaba Vaezi, Wonjae Shin, H. Vincent Poor, Hyundong Shin, Tony Q. S. Quek
2019 arXiv   pre-print
The second one is based on the deep reinforcement learning method that allows all users to share the full bandwidth.  ...  It is shown that the caching-NOMA combination provides a new opportunity of cache hit which enhances the cache utility as well as the effectiveness of NOMA.  ...  To achieve this, we have proposed divide-and-conquer-based and deep-learning-based methods.  ... 
arXiv:1909.11074v1 fatcat:frxzl3vt3bdbvpaen3x4iufpuq

RIS-assisted UAV Communications for IoT with Wireless Power Transfer Using Deep Reinforcement Learning [article]

Khoi Khac Nguyen and Antonino Masaracchia and Tan Do-Duy and H. Vincent Poor and Trung Q. Duong
2021 arXiv   pre-print
We formulate a Markov decision process and propose two deep reinforcement learning algorithms to solve the optimization problem of maximizing the total network sum-rate.  ...  Given the strict requirements of the RIS and UAV, the significant improvement in processing time and throughput performance demonstrates that our proposed scheme is well applicable for practical IoT applications  ...  One of the approaches is deep reinforcement learning (DRL), which is a combination of reinforcement learning and neural networks.  ... 
arXiv:2108.02889v1 fatcat:zzwmzsa6bzc5hb2dvuwcu67x7e

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

Dmitrii Beloborodov, Alexander Ulanov, Jakob Foerster, Shimon Whiteson, Alexander Lvovsky
2020 Machine Learning: Science and Technology  
We use a reinforcement learning agent in conjunction with a quantum-inspired algorithm to solve the Ising energy minimization problem, which is equivalent to the Maximum Cut problem.  ...  Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization.  ...  Acknowledgments We would like to thank Egor Tiunov for providing the manual tuning data and William Clements and Vitaly Kurin for helpful discussions.  ... 
doi:10.1088/2632-2153/abc328 fatcat:4mga2dy4l5hyfe2ub5q3dddt5y

Survey on Machine Learning Algorithms Enhancing the Functional Verification Process

Khaled A. Ismail, Mohamed A. Abd El Ghany
2021 Electronics  
Machine learning (ML) models proved to be valuable for automating major parts of the process, which have typically occupied the bandwidth of engineers; diverting them from adding new coverage metrics to  ...  Therefore, the need for enhancing the process is evident.  ...  Supervised DNN was used in the verification of a cache controller and Q-learning is used as the reinforcement learning RL algorithm on a RISCV-Ariane [10] .  ... 
doi:10.3390/electronics10212688 fatcat:ic2ub7423rcf3exbjatizaoofu

Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction [article]

Pit Schneider
2021 arXiv   pre-print
As an extension of this technique, another contribution comes in the form of a regression model that takes the enhancement potential of a new OCR engine into account.  ...  This especially applies when the underlying data collection is of considerable size and rather diverse in terms of fonts, languages, periods of publication and consequently OCR quality.  ...  Results The machine learning algorithm, coupled to the best observed result, is a regression version of KNN, returning the weighted (based on |B i |) mean of all K neighbours.  ... 
arXiv:2110.01661v3 fatcat:nomweg7ghjdxzbcyrzcfyfmtfi

Enhanced Routing Algorithm Based on Reinforcement Machine Learning—A Case of VoIP Service

Davi Ribeiro Militani, Hermes Pimenta de Moraes, Renata Lopes Rosa, Lunchakorn Wuttisittikulkij, Miguel Arjona Ramírez, Demóstenes Zegarra Rodríguez
2021 Sensors  
It is expected that routing algorithms based on machine learning present advantages using that network data.  ...  Nevertheless, in a routing algorithm based on reinforcement learning (RL) technique, additional control message headers could be required.  ...  In Reference [21] , author uses Deep Reinforcement Learning to develop a new general purpose protocol, and obtained superior results compared to OSPF.  ... 
doi:10.3390/s21020504 pmid:33445691 fatcat:xd5vobm43jb4njghjvjauvh7ba

Deep reinforcement learning based worker selection for distributed machine learning enhanced edge intelligence in internet of vehicles

Junyu Dong, Wenjun Wu, Yang Gao, Xiaoxi Wang, Pengbo Si
2020 Intelligent and Converged Networks  
A Deep Reinforcement Learning (DRL) based solution is proposed, called the Worker Selection based on Policy Gradient (PG-WS) algorithm.  ...  The episodic simulations are built and the REINFORCE algorithm with baseline is used to train the policy network. Results show that the proposed PG-WS algorithm outperforms other comparation methods.  ...  .: Deep reinforcement learning based worker selection for distributed machine learning enhanced : : : 241 Initial weights r 1 ; r 2 ; and r 3 1 comparison methods.  ... 
doi:10.23919/icn.2020.0015 fatcat:tpf2qbs64nhszowhxlamlaff7a

Quantum computing enhanced machine learning for physico-chemical applications [article]

Manas Sajjan, Junxu Li, Raja Selvarajan, Shree Hari Sureshbabu, Sumit Suresh Kale, Rishabh Gupta, Sabre Kais
2021 arXiv   pre-print
In this review we shall explicate a subset of such topics and delineate the contributions made by both classical and quantum computing enhanced machine learning algorithms over the past few years.  ...  In the recent years, it is safe to conclude that ML and its close cousin deep learning (DL) have ushered unprecedented developments in all areas of physical sciences especially chemistry.  ...  The authors made a comparative study of the performances of three reinforcement learning algorithms: tabular Q-learning (TQL), deep Q-learning (DQL), and policy gradient (PG), and two traditionally used  ... 
arXiv:2111.00851v1 fatcat:i2caiglszvbufbyfmf3cwkcduu

Designing an Automated Intelligent e-Learning System to Enhance the Knowledge using Machine Learning Techniques

G Deena, K. Raja
2019 International Journal of Advanced Computer Science and Applications  
This helps the user to fix suitable topics and conveniently generate questions using machine learning techniques.  ...  The modern digital world requires its users to learn continuously in order to enhance their knowledge in the working environment and the academic sector.  ...  In [22] , the author used an agent called mod-knowledge to completely track the learner's knowledge, and the internal and external structure of the learner using the machine learning algorithms.  ... 
doi:10.14569/ijacsa.2019.0101215 fatcat:224tyqhuxfawrdamumjpc6tbd4

Machine Learning Prediction Approach to Enhance Congestion Control in 5G IoT Environment

Ihab Ahmed Najm, Alaa Khalaf Hamoud, Jaime Lloret, Ignacio Bosch
2019 Electronics  
Thus, a new machine learning model based on a decision tree (DT) algorithm is proposed in this study to predict optimal enhancement of congestion control in the wireless sensors of 5G IoT networks.  ...  The dataset was used to train the machine learning model and enable the prediction of optimal alternatives that can enhance the performance of the congestion control approach.  ...  Acknowledgments: The authors would like to thank the anonymous reference and reviewers for their helpful comments that have significantly improved the quality of the presentation.  ... 
doi:10.3390/electronics8060607 fatcat:2yeorc2unjavzno4kj7tq56jmu

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

Hui Zeng, Jianrui Cai, Lida Li, Zisheng Cao, Lei Zhang
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we learn image-adaptive 3-dimensional lookup tables (3D LUTs) to achieve fast and robust photo enhancement. 3D LUTs are widely used for manipulating color and tone of photos, but they are  ...  Recent years have witnessed the increasing popularity of learning-based photo enhancement methods.  ...  [8] introduced a deep reinforcement learning strategy for step-wise image enhancement by learning to predict the discrete probabilities of a set of predefined operators.  ... 
doi:10.1109/tpami.2020.3026740 pmid:32976094 fatcat:3eohl4sq5zhrlebvw2s5xe7ciq

Enhanced Skin Condition Prediction Through Machine Learning Using Dynamic Training and Testing Augmentation

Tryan Aditya Putra, Syahidah Izza Rufaida, Jenq-Shiou Leu
2020 IEEE Access  
In recent years, deep learning has taken the spotlight in automated medical bioimaging.  ...  There is still only limited research focused on dynamic data augmentation, even in the fields of machine learning and computer vision.  ...  However, there is a lot of attention directed at improving machine learning architectures to enhance performance [12] - [15] .  ... 
doi:10.1109/access.2020.2976045 fatcat:7knt2x6z5zaathqjf5gk5gz5zu

Clinical chemistry in higher dimensions: Machine-learning and enhanced prediction from routine clinical chemistry data

Alice Richardson, Ben M. Signor, Brett A. Lidbury, Tony Badrick
2016 Clinical Biochemistry  
Seven myths associated with machine learning and big data are then presented, with the aim of managing expectation of machine learning amongst clinical chemists.  ...  In this review paper, big data and machine learning are defined in terms accessible to the clinical chemistry community.  ...  Products such as SPSS, SAS and even Excel have add-on modules that carry out machine learning algorithms.  ... 
doi:10.1016/j.clinbiochem.2016.07.013 pmid:27452181 fatcat:7botr6zxxbbldlkpnzmrza7ebi

Weak Adhesion Detection – Enhancing the Analysis of Vibroacoustic Modulation by Machine Learning

Benjamin Boll, Erik Willmann, Bodo Fiedler, Robert Horst Meißner
2021 Composite structures  
This study aims to detect weak-bonds due to manufacturing errors or contamination by analysing and interpreting the vibroacoustic modulation signals with the aid of machine learning.  ...  Despite advanced surface treatments and preparations, surface contamination and application errors still occur, resulting in localised areas with a reduced adhesion.  ...  And although tThe analysis 52 of Lamb-wave based experiments with machine learning (ML) methods has 53 been already the subject of several other studies [38-41], applying machine 54 learning methodsHowever  ... 
doi:10.1016/j.compstruct.2021.114233 fatcat:2kex4qql3fcvli2vvng55cfehi
« Previous Showing results 1 — 15 out of 11,961 results