Robotics & Machine Learning Daily News2024,Issue(Jul.1) :133-133.

Suzhou University of Science and Technology Researchers Provide Details of New S tudies and Findings in the Area of Robotics (Robotic arm grasping study combinin g prior knowledge and deep reinforcement learning)

苏州科技大学的研究人员详细介绍了机器人学领域的新研究成果(机械臂抓取学习结合先验知识和深度强化学习)

Robotics & Machine Learning Daily News2024,Issue(Jul.1) :133-133.

Suzhou University of Science and Technology Researchers Provide Details of New S tudies and Findings in the Area of Robotics (Robotic arm grasping study combinin g prior knowledge and deep reinforcement learning)

苏州科技大学的研究人员详细介绍了机器人学领域的新研究成果(机械臂抓取学习结合先验知识和深度强化学习)

扫码查看

摘要

由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-调查人员发布了关于机器人的新报告。根据《中华人民共和国江苏消息》,NewsRx记者的研究表明,"在应用深度强化学习(DRL)实现抢劫手臂自主行为决策的过程中,高维连续状态-行动空间容易导致da ta抽样效率低、经验样本质量低,最终导致奖励函数收敛缓慢,学习时间长"。

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on ro botics. According to news originating from Jiangsu, People’s Republic of China, by NewsRx correspondents, research stated, “In the process of applying deep rein forcement learning (DRL) to realize autonomous behavioral decision-making of rob otic arms, the high-dimensional continuous state-action space is prone to low da ta sampling efficiency and low quality of empirical samples, which ultimately le ads to slow convergence of the reward function and long learning time.”

Key words

Suzhou University of Science and Technol ogy/Jiangsu/People's Republic of China/Asia/Emerging Technologies/Machine L earning/Reinforcement Learning/Robotics/Robots

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文