ETRI-Knowledge Sharing Plaform

Multi-Agent Reinforcement Learning Robot Manipulation An Experimental Study Simulation Results Deep Reinforcement Learning Monitoring System Smart-Eye Partial Observations Power Consumption Control Problem Control Policy Edge Devices Resource-Constrained Image Stitching Disaster Monitoring Deep Learning(DL) Reward Function An Unmanned Aerial Vehicle Video Prediction Computing Systems Computational Power Aerial Images Device Control Dictionary Matrix Disaster Management System Distributed Multi-Agent System Data-Driven Empirical Evaluation Fire Detection High Accuracy High Dispersion Iot Devices Long Horizons Low-Power Multiple Sensors Multi-Robot Number Of Layers Satellite Images Sampled Measurements Training Time Convolution Neural Network(CNN) Compressed Sensing Distributed Network Environment High Resolution Image Hardware Resources Manipulation Performance Pre-Training Reducing Power Real Environment Task Completion Cost-Effective Collaborative Task Cloud Policy Cost-Efficient Convergence Analysis Flight Time Goal-Based Heuristic Information Internet Of Thing(IoT) Limited Information Economic Losses Management Techniques Model Compression Policy Model Policy Training Real-World Applications Residual Energy Sensor Data Virtual World Angle Of View(AoV) Detection Accuracy Embedded System Information Services Key Components Monitoring Techniques Monitoring And Response New Model Optical Sensors Multiple Agents Real-Time Real-World Problems Spatial Resolution Temporal Resolution Visual Representation Cloud Environment Autonomous Driving Average Rewards Digital Communication System Decision Support System(DSS) Deep Neural Network(DNN) Energy-Efficient Energy Consumption Image Set Video Games Action Space Riverside Area Recognition Technique Robotic Manipulation Robot Simulator Smart Manufacturing Simulated Environment Temperature And Humidity Template Matching Collaborative Environment Collaborative Robot Collaborative Manipulation Continuous Action Disaster Information Intrusion Detection System(IDS) Deep Convolutional Neural Networks Experience Replay Learning Approach Learning Environment Break-Down Robot Manipulator Robot Control Social Loafing Trial-And-Error Wild Fire Wide Range Continuous Control Complex Task Area Of Interest Edge Computing Efficient Training Forest Fire Monitoring Human Monitoring Hyper-Connected Knowledge Distillation Link Capacity Knowledge Transfer Control Area Natural Disaster Policy Network Power Control(PC) Performance Comparison Representation Learning Symbol Detection Training Process Time Constraint Task Allocation Camera Angle Cloud Infrastructure Aerial Photographs Analysis Of The Impact Distributed Intelligence Edge Cloud Engineering Methods Empirical Investigation Efficient Communication Human-Like Learning Control Monitoring Service Multimodal Data Nonstationary Environment Policy Optimization Periodic Communication Recovery Method Robot Learning