ReMBo is the first learning-based recommender mechanism for Bayesian stochastic games; it returns policy recommendations with better truthfulness and participation incentives at welfare levels near cooperative MARL baselines.
Multiagent learning in the presence of memory-bounded agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Recommender Mechanisms for Bayesian Stochastic Games
ReMBo is the first learning-based recommender mechanism for Bayesian stochastic games; it returns policy recommendations with better truthfulness and participation incentives at welfare levels near cooperative MARL baselines.