SICA combines selective state-space filtering with attention-based training-time communication and a regeneration module to let MARL agents coordinate without messages at execution time.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tacit Learning with Adaptive Information Selection for Cooperative Multi-Agent Reinforcement Learning
SICA combines selective state-space filtering with attention-based training-time communication and a regeneration module to let MARL agents coordinate without messages at execution time.