AELA improves MARL training by starting with truncated episodes and lengthening them when action-entropy falls, showing gains over QMIX and VDN on SMAC and predator-prey tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MA 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning
AELA improves MARL training by starting with truncated episodes and lengthening them when action-entropy falls, showing gains over QMIX and VDN on SMAC and predator-prey tasks.