Results 261 to 270 of about 1,629,210 (315)

Deep Q-Networks

2020
This chapter aims to introduce one of the most important deep reinforcement learning algorithms, called deep Q-networks. We will start with the Q-learning algorithm via temporal difference learning, and introduce the deep Q-networks algorithm and its variants.
openaire   +1 more source

Robot Soccer Using Deep Q Network

2018 International Conference on Platform Technology and Service (PlatCon), 2018
Reinforcement Learning is one of brilliant way to develop intelligent agents in the field of Artificial Intelligence. This paper proposes a RL algorithm called Deep Q Network and presents applications of this algorithm to the decision-making problems challenged in the RoboCup.
Jinwon Kim, Bongsu Kim, Jinwoo Yoon, Marley Lee, Sunah Jung, Jae young Choi   +5 more
openaire   +1 more source

Task Offloading and Resource Allocation for Industrial Internet of Things: A Double-Dueling Deep Q-Network Approach

IEEE Access, 2022
With the development of 5G technology, Mobile Edge Computing (MEC) has become a promising technology that is widely used in the Industrial Internet of Things (IIoT) and other fields.
Weijun Cheng, Xiaoshi Liu, Xiaoting Wang, Gaofeng Nie   +3 more
semanticscholar   +1 more source

QADQN: Quantum Attention Deep Q-Network for Financial Market Prediction

International Conference on Quantum Computing and Engineering
Financial market prediction and optimal trading strategy development remain challenging due to market complexity and volatility. Our research in quantum finance and reinforcement learning for decision-making demonstrates the approach of quantum-classical
Siddhant Dutta, Nouhaila Innan, Alberto Marchisio, S. Yahia, Muhammad Shafique   +4 more
semanticscholar   +1 more source

A Fault Diagnosis Method Based on an Improved Deep Q-Network for the Interturn Short Circuits of a Permanent Magnet Synchronous Motor

IEEE Transactions on Transportation Electrification
With the rapid development of artificial intelligence, deep learning has become a widely used method to monitor the state of permanent magnet synchronous motors (PMSMs).
Yuanjiang Li, Ruiqi Wang, Runze Mao, Yan Zhang, Kai Zhu, Yuanjun Li, Jinglin Zhang   +6 more
semanticscholar   +1 more source

On Joint Offloading and Resource Allocation: A Double Deep Q-Network Approach

IEEE Transactions on Cognitive Communications and Networking, 2021
Multi-access edge computing (MEC) is an important enabling technology for 5G and 6G networks. With MEC, mobile devices can offload their computationally heavy tasks to a nearby server which can be a simple node at a base station, a vehicle or another ...
Fahime Khoramnejad, M. Erol-Kantarci
semanticscholar   +1 more source

Multi-agent Double Deep Q-Networks

2017
There are many open issues and challenges in the multi-agent reward-based learning field. Theoretical convergence guarantees are lost, and the complexity of the action-space is also exponential to the amount of agents calculating their optimal joint-action.
David Simões, Nuno Lau, Luís Paulo Reis   +2 more
openaire   +1 more source

Reversible Data Hiding for Color Images Based on Adaptive 3D Prediction-Error Expansion and Double Deep Q-Network

IEEE transactions on circuits and systems for video technology (Print), 2022
Reversible data hiding (RDH) for color images has attracted increasing attention in recent years. Due to its effective utilization of the correlation between prediction errors, high-dimensional prediction-error expansion (PEE) can achieve much better ...
Jie Chang, Guopu Zhu, Hongli Zhang, Yicong Zhou, Xiangyang Luo, Ligang Wu   +5 more
semanticscholar   +1 more source

A New Subsampling Deep Q Network Method

2020 International Conference on Computer Network, Electronic and Automation (ICCNEA), 2020
In view of the sampling mechanism of experience replay in traditional deep reinforcement learning algorithm, the random sampling mechanism only samples the samples with equal probability without considering the importance of the samples, which may lead to excessive use of samples with low amount of information in the training process. In order to solve
Yabing Guan, Bailin Liu, Jiangwei Zhou, Wenjing Wang   +3 more
openaire   +1 more source

Deep Q-Network Using Reward Distribution

2018
In this paper, we propose a Deep Q-Network using reward distribution. Deep Q-Network is based on the convolutional neural network which is a representative method of Deep Learning and the Q Learning which is a representative method of reinforcement learning.
Yuta Nakaya, Yuko Osana
openaire   +1 more source