2 papers
cs.LG2025
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
Alsu Sagirova, Yuri Kuratov, Mikhail Burtsev
Coordination in decentralized multi-agent reinforcement learning (MARL) necessitates that agents share information about their behavior and intentions. Existing approaches rely on…
cs.CL2024
Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task
Alsu Sagirova, Mikhail Burtsev
Even though Transformers are extensively used for Natural Language Processing tasks, especially for machine translation, they lack an explicit memory to store key concepts of proce…