In a multi-agent resource race, independent Q-learning agents alternate less often than random policies, while conventional fairness/efficiency metrics hide the deficit.
Loss aversion fosters coordination amongindependentreinforcementlearners,
1 Pith paper cite this work, alongside 5 external citations. Polarity classification is still indexing.
1
Pith paper citing it
5
external citations · OpenAlex
fields
cs.MA 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Coordination Gap: Multi-Agent Alternation Metrics for Temporal Fairness in Repeated Games
In a multi-agent resource race, independent Q-learning agents alternate less often than random policies, while conventional fairness/efficiency metrics hide the deficit.