首页|Studies from Guilin University of Aerospace Technology in the Area of Robotics D escribed (Improved Double Deep Q Network Algorithm Based On Average Q-value Esti mation and Reward Redistribution for Robot Path Planning)
Studies from Guilin University of Aerospace Technology in the Area of Robotics D escribed (Improved Double Deep Q Network Algorithm Based On Average Q-value Esti mation and Reward Redistribution for Robot Path Planning)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews - A new study on Robotics is now available. Accordi ng to news reporting out of Guilin, People’sRepublic of China, by NewsRx editor s, research stated, “By integrating deep neural networks with reinforcementlear ning, the Double Deep Q Network (DDQN) algorithm overcomes the limitations of Qlearningin handling continuous spaces and is widely applied in the path plannin g of mobile robots. However,the traditional DDQN algorithm suffers from sparse rewards and inefficient utilization of high-qualitydata.”
GuilinPeople’s Republic of ChinaAsiaAlgorithmsEmerging TechnologiesMachine LearningRobotRoboticsGuilin U niversity of Aerospace Technology