Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

By Hangyu Mao, Wulong Liu, Jianye Hao, Jun Luo, Dong Li, Zhengchao Zhang, Jun Wang, Zhen Xiao. 2019

85 citations recorded by the source corpus.

Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation. Meanwhile, only cognitive consistency within a neighborhood matters because humans only interact directly with their neighbors. Inspired by these observations, we take the first step to introduce \emph{neighborhood cognitive consistency} (NCC) into multi-agent reinforcement learning (MARL). Our NCC design is quite general and can be easily combined with existing MARL methods. As examples, we propose neighborhood cognition consistent deep Q-learning and Actor-Critic to facilitate large-scale multi-agent cooperations. Extensive experiments on several challenging tasks (i.e., packet routing, wifi configuration, and Google football player control) justify the superior performance of our methods compared with state-of-the-art MARL approaches.

Subfields: Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical and Nonlinear Physics

Citations in the corpus

Celebrating Diversity in Shared Multi-Agent Reinforcement Learning (2021, background): “There are other works that investigate into MARL from the perspective of coordination graphs [28–30], communication [31, 32, 15], and role-based learning [17, 33].”
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition (2021, background): “…decision-making tasks, such as multi-player games (Berner et al., 2019; Vinyals et al., 2019; Ye et al., 2020), resource allocation (Zimmer et al., 2021; Sheng et al., 2022), and network routing (Mao et al., 2020a;b), is a signiﬁcant problem in cooperative multi-agent reinforcement learning (MARL).”