KD-MARL distills both actions and coordination structure from expert MARL policies into heterogeneous lightweight students, retaining over 90% performance while cutting FLOPs by up to 28.6 times on SMAC and MPE benchmarks.
Dealing with non-stationarity in decentralized cooperative multi-agent deep reinforcement learning via multi-timescale learning, in: Conference on Lifelong Learning Agents, PMLR
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning
KD-MARL distills both actions and coordination structure from expert MARL policies into heterogeneous lightweight students, retaining over 90% performance while cutting FLOPs by up to 28.6 times on SMAC and MPE benchmarks.