.png){kind=icon}
Return
State-based episodic memory for multi-agent reinforcement learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10994-023-06365-2.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the sample inefficiency problem. In this paper, we propose a simple yet effective approach, called state-based episodic memory (SEM), to improve sample efficiency in MARL. SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL. To the best of our knowledge, SEM is the first work to introduce EM into MARL. SEM has lower space complexity and time complexity than state and action based EM (SAEM) initially proposed for single-agent reinforcement learning when using for MARL. Experimental results on two synthetic environments and one real environment show that introducing episodic memory into MARL can improve sample efficiency, and SEM can reduce storage cost and time cost compared with SAEM.
Keywords:
Multi-agent
Reinforcement learning
Episodic memory
Sample efficiency
Journal
IF:
2.9
Papers:
2.7K
Citations:
3.4W
Organization
Cited Papers
ShareSaveShareSaveA general criterion and an algorithmic framework for learning in multi-agent systems.png)
MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAIShareSaveShareSaveShareSaveShareSave
View more