observation-structure

Tag

Cards List
#observation-structure

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

arXiv cs.AI · 2026-06-30 Cached

HiComm is a plug-in communication module for cooperative multi-agent reinforcement learning that grounds messages in the sender's hierarchical observation structure, using a receiver-driven query and three-stage decoding to reduce communication volume by up to 23x.

0 favorites 0 likes
← Back to home

Submit Feedback