MLSP-L20.4
Adaptive parameter sharing for multi-agent reinforcement learning
Dapeng Li, Institute of Automation, Chinese Academy of Sciences. School of Artificial Intelligence, University of Chinese Academy of Sciences., China; Na Lou, Institute of Automation, Chinese Academy of Sciences, China; Bin Zhang, Zhiwei Xu, Guoliang Fan, Institute of Automation, Chinese Academy of Sciences, China
Session:
MLSP-L20: Reinforcement Learning I Lecture
Track:
Machine Learning for Signal Processing
Location:
Room 105
Presentation Time:
Fri, 19 Apr, 09:20 - 09:40 (UTC +9)
Session Co-Chairs:
Ville Hautamäki, University of Eastern Finland and Che Lin, National Taiwan University
Session MLSP-L20
MLSP-L20.1: MULTI-AGENT EXPLORATION VIA SELF-LEARNING AND SOCIAL LEARNING
Shaokang Dong, Chao Li, Wubing Chen, Hongye Cao, Wenbin Li, Yang Gao, Nanjing University, China
MLSP-L20.2: M$^3$ARL: Moment-Embedded Mean-Field Multi-Agent Reinforcement Learning for Continuous Action Space
Huaze Tang, Yuanquan Hu, Fanfan Zhao, Junji Yan, Ting Dong, Wenbo Ding, Tsinghua University, China
MLSP-L20.3: Zero-shot Imitation Policy via Search in Demonstration Dataset
Federico Malato, University of Eastern Finland, Finland; Florian Leopold, Andrew Melnik, Bielefeld University, Germany; Ville Hautamäki, University of Eastern Finland, Finland
MLSP-L20.4: Adaptive parameter sharing for multi-agent reinforcement learning
Dapeng Li, Institute of Automation, Chinese Academy of Sciences. School of Artificial Intelligence, University of Chinese Academy of Sciences., China; Na Lou, Institute of Automation, Chinese Academy of Sciences, China; Bin Zhang, Zhiwei Xu, Guoliang Fan, Institute of Automation, Chinese Academy of Sciences, China
MLSP-L20.5: A META-PRECONDITIONING APPROACH FOR DEEP Q-LEARNING
Spilios Evmorfos, Athina Petropulu, RUTGERS UNIVERSITY, United States of America
MLSP-L20.6: MEPE: A Minimalist Ensemble Policy Evaluation Operator for Deep Reinforcement Learning
Qiang He, Xinwen Hou, Institute of Automation, Chinese Academy of Sciences, Germany
Contacts