Q-Learning in Regularized Mean-field Games.

Berkay Anahtarci Can Deha Kariksiz Naci Saldi

Published in: CoRR (2020)

Keyphrases

reinforcement learning
function approximation
cooperative
multi agent
multiagent learning
game playing
least squares

markov random field
game design
computer games
video games
markov networks
statistical mechanics
state space

bayesian inference
game theory
learning rate
closed form
action selection
multi agent reinforcement learning
game play

nash equilibria
linear complexity
stochastic games
learning agents
dynamic programming
pairwise