ETRI-Knowledge Sharing Plaform

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