Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning
Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson
备注:
This work as been accepted as an Extended Abstract in Proc. of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), N. Agmon, M. E. Taylor, E. Elkind, M. Veloso (eds.), May 2019, Montreal, Canada
Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in [4] and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements.
Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
针对合作多智能体强化学习中IGM原则限制问题,提出双自感知价值分解框架,结合自我策略与 alter ego 价值函数并引入反自我探索机制,实现完全无需IGM的价值分解并在多任务中表现优异。
Analysing the behaviour of robot teams through relational sequential pattern mining
University of Bari “Aldo Moro”(巴里大学“阿尔多·莫罗”);Imperial College(帝国理工学院);IIIA - Artificial Intelligence Research Institute, CSIC - Spanish Council for Scientific Research(西班牙国家研究委员会人工智能研究所(IIIA))
School of Computer and Information Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University(北京交通大学交通数据分析与挖掘北京市重点实验室)
Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University(清华大学交叉信息研究院);Department of Computer Science, University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系);Harvard University(哈佛大学)
Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus
The Hong Kong University of Science and Technology(香港科学与技术大学);The Hong Kong Polytechnic University(香港理工大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州))
Physics-Informed Multi-Agent Reinforcement Learning for Distributed Multi-Robot Problems
DIIS - I3A, Universidad de Zaragoza(迪斯-伊3A,阿尔瓦尔萨大学);Department of Electrical and Computer Engineering, University of California San Diego(电气与计算机工程系,加州大学圣地亚哥分校)