Hamido Fujita教授:On new Trends in Deep Reinforcement Learning: Different deep policy based gradients(深度强化学习的新趋势:不同的基于深度策略的梯度)

11月1日 14:00-15:30,腾讯会议:424-818-680

发布者:缪月琴发布时间:2023-10-30浏览次数:8948

讲座内容:On new Trends in Deep Reinforcement Learning: Different deep policy based gradients(深度强化学习的新趋势:不同的基于深度策略的梯度)

讲座人:Hamido Fujita教授

讲座时间:11月1日 14:00-15:30

腾讯会议:424-818-680


Abstract:

   In recent years, deep reinforcement learning (DRL) has made significant progress in the field of artificial intelligence. This abstract mainly focuses on a novel DRL method, namely the Different Deep Policy based Gradients (DDPG) method based on different depth strategies. DDPG combines the advantages of deep neural networks in function approximation and the advantages of strategy gradient methods in optimizing strategies, providing new ideas for intelligent agents to achieve efficient learning in complex environments.


Short Bio:

   He is Executive Chairman of i-SOMET Incorporated Association, Japan, and  Distinguished Professor at Iwate Prefectural University, Japan, he is also Research  Professor at University of Granada, Spain. He is Highly Cited Researcher in CrossField for the year 2019 and in Computer Science for the year 2020, 2021 and 2022, by  Clarivate Analytics. He received Doctor Honoris Causa from Óbuda University,  Budapest, Hungary, in 2013 and received Doctor Honoris Causa from Timisoara  Technical University, Timisoara, Romania, in 2018, and a title of Honorary Professor  from Óbuda University, in 2011. He is Distinguished Research Professor at the  University of Granada, and Adjunct Professor with Taipei Technical University,  Taiwan, Harbin Engineering University, China and others. He supervised Ph.D.  students jointly with the University of Laval, Quebec City, QC, Canada; University of  Technology Sydney; Oregon State University, Corvallis, OR, USA; University of Paris  1 Pantheon-Sorbonne, Paris, France; and University of Genoa, Italy. Dr. Fujita is the  recipient of the Honorary Scholar Award from the University of Technology Sydney,  in 2012. He was the Editor-in-Chief for Knowledge-Based Systems (Elsevier) (2005- 2019) and then Emeritus Editor of Knowledge-Based Systems in 2020~. Since 2020  he is currently the Editor-in-Chief of Applied Intelligence (Springer) and the Editor-inChief of International Journal of Healthcare Management (Taylor & Francis). He  headed a number of projects including intelligent HCI, a project related to mental  cloning for healthcare systems as an intelligent user interface between human-users and  computers, and SCOPE project on virtual doctor systems for medical applications. He  collaborated with several research projects in Europe, and recently he is collaborating  in OLIMPIA project supported by Tuscany region on Therapeutic monitoring of  Parkison disease. He has published more than 400 articles mainly in high impact factor journals.


Baidu
sogou