Tag
HyPOLE introduces a framework for multi-agent reinforcement learning under partial observability that uses hyperproperty-guided learning via HyperLTL temporal logic, integrated with centralized training for decentralized execution, and demonstrates improvements over baselines on SMAC, MessySMAC, and WildFire benchmarks.
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.
Introduces HPML, a method that projects the joint update field of multi-agent systems onto a metric-gradient component to stabilize and improve multi-agent reinforcement learning. It provides theoretical guarantees and shows improved stability and returns on CTDE benchmarks.
Proposes MAVIC, a method for multi-agent reinforcement learning that corrects value estimates at instruction boundaries to enable compliance with external natural language instructions while preserving base task performance.