Networked Policy Gradient Play in Markov Potential Games.

Sarper Aydin Ceyhun Eksin

Published in: ICASSP (2023)

Keyphrases

policy gradient
game playing
game theory
computer games
reinforcement learning
imperfect information
game play
markov model
actor critic
model free reinforcement learning
machine learning
cooperative
cost function
video games
optimal control
approximate solutions