Exploiting Structure and Agent-Centric Rewards to Promote Coordination in Large Multiagent Systems

How researchers see this paper

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

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning (2019, background): “Multi-domain Gaussian Squeeze (MGS) Gaussian Squeeze (GS) (HolmesParker et al., 2014) is a simple nonmonotonic multi-agent resource allocation problem, used in other papers, e.g., Yang et al. (2018) and Chen et al. (2018).”
Mean Field Multi-Agent Reinforcement Learning (2018, background): “In the Gaussian Squeeze (GS) task (HolmesParker et al., 2014), N homogeneous agents determine their individual action a j to jointly optimize the most appropriate summation x = ∑N j=1 a j .”
A review of cooperative multi-agent deep reinforcement learning (2019, methodology): “In the experimental analysis, the comparisons of QTRAN with VDN and QMIX on Multi-domain Gaussian Squeeze [46] and modiﬁed predator-prey [124] is provided.”
QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning (2020, background): “The MGS environment is specially designed for demonstrating the ability of QTRAN to learn non-monotonic action-value estimators; it modiﬁes the Gaussian squeeze environment (HolmesParker et al., 2014) to have multiple agent-wise policies that achieve locally optimal performance.”