A minorization-maximization scheme converges to the potential-optimal equilibrium in regularized coordination games with irrational agents and is shown to be an epsilon-equilibrium of the original game.
Exploration in deep reinforcement learning: From single-agent to multi agent domain
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.GT 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learning Equilibria in Coordination Games via Minorization-Maximization
A minorization-maximization scheme converges to the potential-optimal equilibrium in regularized coordination games with irrational agents and is shown to be an epsilon-equilibrium of the original game.