BiDist trains MARL agents to handle unseen co-players by using forward and reverse distillation to generate diverse partner behaviors without storing past policies.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors
BiDist trains MARL agents to handle unseen co-players by using forward and reverse distillation to generate diverse partner behaviors without storing past policies.