A curriculum that grows the number of agents over training, combined with a graph neural network that accepts variable agent counts, improves large-scale multiagent RL performance in StarCraft II and MAgent.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Few to More: Large-scale Dynamic Multiagent Curriculum Learning
A curriculum that grows the number of agents over training, combined with a graph neural network that accepts variable agent counts, improves large-scale multiagent RL performance in StarCraft II and MAgent.