RM-FSP: Regret minimization optimizes neural fictitious self-play.

Yuxuan Chen Li Zhang Shijian Li Xili Chen Gang Pan Zhijie Pan

Published in: Neurocomputing (2023)

Keyphrases

regret minimization
nash equilibrium
game theoretic
neural network
network architecture
neural model
multi agent learning
neural fuzzy
game theory
domain knowledge
bio inspired
artificial neural
upper bound
associative memory
learning rules
nonlinear predictive control