4.7 Article

Multiagent Reinforcement Learning With Heterogeneous Graph Attention Network

Journal

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3215774

Keywords

Reinforcement learning; Multi-agent systems; Aggregates; Task analysis; Scalability; Marine vehicles; Learning systems; Graph attention network; heterogeneous agents; multiagent reinforcement learning (MARL); relationship-level attention

Ask authors/readers for more resources

Most recent research on MARL has focused on deploying cooperative policies for homogeneous agents, but realistic multiagent environments may have heterogeneous agents. To tackle the challenges posed by heterogeneity and diverse relationships, the researchers propose a novel method that uses a heterogeneous graph attention network to model the relationships between heterogeneous agents.
Most recent research on multiagent reinforcement learning (MARL) has explored how to deploy cooperative policies for homogeneous agents. However, realistic multiagent environments may contain heterogeneous agents that have different attributes or tasks. The heterogeneity of the agents and the diversity of relationships cause the learning of policy excessively tough. To tackle this difficulty, we present a novel method that employs a heterogeneous graph attention network to model the relationships between heterogeneous agents. The proposed method can generate an integrated feature representation for each agent by hierarchically aggregating latent feature information of neighbor agents, with the importance of the agent level and the relationship level being entirely considered. The method is agnostic to specific MARL methods and can be flexibly integrated with diverse value decomposition methods. We conduct experiments in predator-prey and StarCraft Multiagent Challenge (SMAC) environments, and the empirical results demonstrate that the performance of our method is superior to existing methods in several heterogeneous scenarios.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available