A decentralized UCB variant learns unknown coordination thresholds and avoids decoy arms, reportedly approaching oracle-level cumulative reward in a small simulated environment.
Threshold bandits, with and without cen- sored feedback
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
-
Learning to Coordinate Under Threshold Rewards: A Cooperative Multi-Agent Bandit Framework
A decentralized UCB variant learns unknown coordination thresholds and avoids decoy arms, reportedly approaching oracle-level cumulative reward in a small simulated environment.