2 papers
cs.MA2025
ToMacVF : Temporal Macro-action Value Factorization for Asynchronous Multi-Agent Reinforcement Learning
Wenjing Zhang, Wei Zhang
Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-action…
cs.AI2024
SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition
Wenjing Zhang, Wei Zhang
Instead of making behavioral decisions directly from the exponentially expanding joint observational-action space, subtask-based multi-agent reinforcement learning (MARL) methods e…