Code for the paper "Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems" accepted at AAAI 2025. TGNet is is implemented in PyTorch and tested on challenging tasks SMAC, LBF and Hallway as benchmarks, which is based on EPyMARL.
-
Notifications
You must be signed in to change notification settings - Fork 0
ZhuohuiZhang/TGCNet
About
This is the official implementation of [AAAI'25] accepted paper: Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published