Graph Convolutional Reinforcement Learning for Multi-Agent Cooperation

15 citations recorded by the source corpus.

How researchers see this paper

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

Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication (2020, neutral): “However, DGN considers a diﬀerent problem setting where local rewards are presented to agents, while our method provides only global rewards.”
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms (2019, background): “Following [21], various works [343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354] have proposed a variety of neural network architectures to foster communication among agents.”
Learning Transferable Cooperative Behavior in Multi-Agent Teams (2019, methodology): “DGN (Jiang et al., 2018) also uses a similar mechanism for communication but with Q-learning (Mnih et al.”
When2com: Multi-Agent Perception via Communication Graph Grouping (2020, background): “Recent works have proposed to construct communication groups based on pre-defined rules [18, 17] or a unified communication network [33, 34, 15, 28, 33, 6].”
CoLight: Learning Network-level Cooperation for Traffic Signal Control (2019, background): “The attention mechanism is employed widely in diverse domains to boost model accuracy [5, 14, 32, 33].”
A review of cooperative multi-agent deep reinforcement learning (2019, methodology): “, 2018 [54] 1 Q 0 (L,L) (L,L) (L,L) Iqbal and Sha, 2019 [50] 1 AC 0 (G,L) (G,L) (G,L) Yang et al.”