Filters








12,165 Hits in 5.7 sec

Deep Graph Reinforcement Learning Based Intelligent Traffic Routing Control for Software-Defined Wireless Sensor Networks

Ru Huang, Wenfan Guan, Guangtao Zhai, Jianhua He, Xiaoli Chu
2022 Applied Sciences  
In this paper we propose a deep graph reinforcement learning (DGRL) model-based intelligent traffic control scheme for SDWSNs, which combines graph convolution with deterministic policy gradient.  ...  The model fits well for the task of intelligent routing control for the SDWSN, as the process of data forwarding can be regarded as the sampling of continuous action space and the traffic data has strong  ...  Data Availability Statement: Not applicable.  ... 
doi:10.3390/app12041951 fatcat:m6he66qvt5diff5xtp4rzxais4

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Junyan Chen, Yong Wang, Jiangtao Ou, Chengyuan Fan, Xiaoye Lu, Cenhuishan Liao, Xuefeng Huang, Hongmei Zhang
2022 Wireless Communications and Mobile Computing  
This paper proposes an automatic load-balancing architecture based on reinforcement learning (ALBRL) in SDN.  ...  In this architecture, we design a load-balancing optimization model in high-load traffic scenarios and adapt the improved Deep Deterministic Policy Gradient (DDPG) algorithm to find a near-optimal path  ...  Network Architecture In this paper, we describe our designed network architecture based on deep reinforcement learning, as shown in Figure 1 .  ... 
doi:10.1155/2022/3866143 doaj:70728784e5614b20b16b7379678158b8 fatcat:wekijwdc6jeilgtniiwv2t5lhe

The Control Method of Twin Delayed Deep Deterministic Policy Gradient with Rebirth Mechanism to Multi-DOF Manipulator

Yangyang Hou, Huajie Hong, Zhaomei Sun, Dasheng Xu, Zhe Zeng
2021 Electronics  
This paper further suppresses the overestimation bias of values for multi-degree of freedom (DOF) manipulator learning based on deep reinforcement learning.  ...  Twin Delayed Deep Deterministic Policy Gradient with Rebirth Mechanism (RTD3) was proposed.  ...  These two aspects are: one is to design a new deep reinforcement learning network structure based on TD3; the other is to design a new reward function 'step-by-step reward function'.  ... 
doi:10.3390/electronics10070870 fatcat:4u2liupf6jcpvg4nnculdma3yq

Emergence of human-comparable balancing behaviours by deep reinforcement learning

Chuanyu Yang, Taku Komura, Zhibin Li
2017 2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)  
This paper presents a hierarchical framework based on deep reinforcement learning that learns a diversity of policies for humanoid balance control.  ...  The successful emergence of humanlike behaviors through deep reinforcement learning proves the feasibility of using an AI-based approach for learning humanoid balancing control in a unified framework.  ...  In this paper, we propose a novel framework based on deep reinforcement learning that can make use of under-actuated behavior for keeping the balance during standing.  ... 
doi:10.1109/humanoids.2017.8246900 dblp:conf/humanoids/YangKL17 fatcat:zak7o5wsfvbujk6tflxawqqnee

Emergence of Human-comparable Balancing Behaviors by Deep Reinforcement Learning [article]

Chuanyu Yang, Taku Komura, Zhibin Li
2018 arXiv   pre-print
This paper presents a hierarchical framework based on deep reinforcement learning that learns a diversity of policies for humanoid balance control.  ...  The successful emergence of human-like behaviors through deep reinforcement learning proves the feasibility of using an AI-based approach for learning humanoid balancing control in a unified framework.  ...  In this paper, we propose a novel framework based on deep reinforcement learning that can make use of under-actuated behavior for keeping the balance during standing.  ... 
arXiv:1809.02074v1 fatcat:255popwpubgubocofmlakqrzve

Unexpected Collision Avoidance Driving Strategy Using Deep Reinforcement Learning

Myounghoe Kim, Seongwon Lee, Jaehyun Lim, Jongeun Choi, Seong Gu Kang
2020 IEEE Access  
We used a deep deterministic policy gradient method in the simulated environment to train self-driving agents.  ...  In this paper, we generated intelligent self-driving policies that minimize the injury severity in unexpected traffic signal violation scenarios at an intersection using the deep reinforcement learning  ...  In [17] , a deep neural network is used for function estimation of value-based reinforcement learning. This method is applicable only to tasks with discrete action space.  ... 
doi:10.1109/access.2020.2967509 fatcat:bnvhmusxkban5lwa5tgzhtimda

Local Planners with Deep Reinforcement Learning for Indoor Autonomous Navigation

Mauro Martini, Vittorio Mazzia, Simone Angarano, Dario Gandini, Marcello Chiaberge
2021 Zenodo  
In the last years, Deep Reinforcement Learning (DRL) has proven to be a competitive short-range guidance system solution for power-efficient and low computational cost point-to-point local planners.  ...  Index Terms—Indoor Autonomous Navigation, Autonomous Agents, Deep Reinforcement Learning  ...  METHODOLOGY Deep Deterministic Policy Gradient (DDPG) [10] is the specific Deep Reinforcement Learning (DRL) algorithm used to train an agent in a custom virtual environment realized in Gazebo.  ... 
doi:10.5281/zenodo.6367976 fatcat:fhkhugbbirhuhnlnnle22cu2ii

Local Planners with Deep Reinforcement Learning for Indoor Autonomous Navigation

Mauro Martini, Vittorio Mazzia, Simone Angarano, Dario Gandini, Marcello Chiaberge
2021 Zenodo  
In the last years, Deep Reinforcement Learning (DRL) has proven to be a competitive short-range guidance system solution for power-efficient and low computational cost point-to-point local planners.  ...  Index Terms—Indoor Autonomous Navigation, Autonomous Agents, Deep Reinforcement Learning  ...  METHODOLOGY Deep Deterministic Policy Gradient (DDPG) [10] is the specific Deep Reinforcement Learning (DRL) algorithm used to train an agent in a custom virtual environment realized in Gazebo.  ... 
doi:10.5281/zenodo.5900628 fatcat:npqebwyoujbbpnszxe22moamiy

Learning to drive via Apprenticeship Learning and Deep Reinforcement Learning [article]

Wenhui Huang and Francesco Braghin and Zhuo Wang
2020 arXiv   pre-print
We use gradient inverse reinforcement learning (GIRL) algorithm to recover the unknown reward function and employ REINFORCE as well as Deep Deterministic Policy Gradient algorithm (DDPG) to learn the optimal  ...  Therefore, we propose an apprenticeship learning in combination with deep reinforcement learning approach that allows the agent to learn the driving and stopping behaviors with continuous actions.  ...  Reinforcement Learning is learning what to do-how to map situations to actions-so as to maximize a numeral reward [15] . In [16] a deep Q-network (DQN) algorithm is utilized as a decision maker.  ... 
arXiv:2001.03864v1 fatcat:emytu35udfbyzep4keydyhkrdm

Bipedal Walking Robot using Deep Deterministic Policy Gradient [article]

Arun Kumar, Navneet Paul, S N Omkar
2018 arXiv   pre-print
The autonomous walking of the BWR is achieved using reinforcement learning algorithm called Deep Deterministic Policy Gradient(DDPG).  ...  DDPG is one of the algorithms for learning controls in continuous action spaces.  ...  Our contributions in this research: • Suggest a framework for implementing reinforcement learning algorithms in Gazebo simulator environment. • Implement Deep Deterministic Policy Gradient based RL algorithm  ... 
arXiv:1807.05924v2 fatcat:pziod2pmxffkxivw3sjy2i3rbu

A Deep-Reinforcement Learning Approach for Software-Defined Networking Routing Optimization [article]

Giorgio Stampa, Marta Arias, David Sanchez-Charles, Victor Muntes-Mulero, Albert Cabellos
2017 arXiv   pre-print
In this paper we design and evaluate a Deep-Reinforcement Learning agent that optimizes routing.  ...  Our agent adapts automatically to current traffic conditions and proposes tailored configurations that attempt to minimize the network delay. Experiments show very promising performance.  ...  This new networking paradigm is referred to as Knowledge-Defined Networking (KDN) [5] . In this paper we focus on the use of a Deep-Reinforcement Learning (DRL) agent for routing optimization.  ... 
arXiv:1709.07080v1 fatcat:opqz54rh5nhgda7s3jxtsixsuu

Intrusion Detection Based on Generative Adversarial Network of Reinforcement Learning Strategy for Wireless Sensor Networks

Jun Tu, Willies Ogola, Dehong Xu, Wei Xie
2022 North atlantic university union: International Journal of Circuits, Systems and Signal Processing  
In our work, we research on a novel machine learning algorithm on intrusion detection based on reinforcement learning (RL) strategy using generative adversarial network (GAN) for WSN which can automatically  ...  networks data against adversaries and improves on the accuracy of the detection.  ...  Jun Tu for the support after a whole year of reading, researching, developing, testing and finally, being able to write my this paper.  ... 
doi:10.46300/9106.2022.16.58 fatcat:h5kkd3y7dvesng2bmqym7xeblm

Guest Editorial: Special Issue on AI-Enabled Internet of Dependable and Controllable Things

Wei Yu, Wei Zhao, Anke Schmeink, Houbing Song, Guido Dartmann
2021 IEEE Internet of Things Journal  
See https://www.ieee.org/publications/rights/index.html for more information. the reliability of network links, as well as a deep deterministic policy gradient algorithm to compute the forwarding paths  ...  The article titled "CDDPG: A deep-reinforcement-learningbased approach for electric vehicle charging control" proposes Digital Object Identifier 10.1109/JIOT.2021.3053713 a deep reinforcement-learning-based  ... 
doi:10.1109/jiot.2021.3053713 fatcat:wnsgkuohhvg4fitk6ixreddsly

DESOLATER: Deep Reinforcement Learning-based Resource Allocation and Moving Target Defense Deployment Framework

Seunghyun Yoon, Jin-Hee Cho, Dan Dongseong Kim, Terrence J. Moore, Frederica Free-Nelson, Hyuk Lim
2021 IEEE Access  
To this end, we propose, DESOLATER (Drl-based rESOurce aLlocation And mTd dEployment fRamework), which is a multi-agent deep reinforcement learning (mDRL)-based network slicing technique that can help  ...  INDEX TERMS Deep reinforcement learning, in-vehicle network, moving target defense, network slicing, partial observability, software-defined networking.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.  ... 
doi:10.1109/access.2021.3076599 fatcat:bls3yfio5reojcx44aplg5ujum

Motion planning for mobile Robots–focusing on deep reinforcement learning: A systematic Review

Huihui Sun, Weijie Zhang, Runxiang YU, Yujie Zhang
2021 IEEE Access  
This paper reviews the methods based on motionplanning policy, especially the ones involving Deep Reinforcement Learning (DRL) in the unstructured environment.  ...  INDEX TERMS Mobile robot; Deep reinforcement learning; Motion planning  ...  [137] designed a hybrid reinforcement learning motion planning method based on the mechanical motion planning method.  ... 
doi:10.1109/access.2021.3076530 fatcat:53kdh5cfgvcang5xymf4vrqx2e
« Previous Showing results 1 — 15 out of 12,165 results