Independent agents in a static mean-field game reach approximate Nash equilibrium under monotone payoffs, with finite-sample exploitability bounds for full and bandit feedback.
Hysteretic q-learning: an algorithm for decentralized reinforcement learning in cooperative multi-agent teams
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Variational Inequality Approach to Independent Learning in Static Mean-Field Games
Independent agents in a static mean-field game reach approximate Nash equilibrium under monotone payoffs, with finite-sample exploitability bounds for full and bandit feedback.