Model-Free Value Iteration Solution for Dynamic Graphical Games.

Mohammed I. Abouheaf Wail Gueaieb

Published in: CIVEMSA (2018)

Keyphrases

model free
policy iteration
reinforcement learning
reinforcement learning algorithms
average reward
function approximation
markov decision processes
heuristic search
policy evaluation
dynamic environments
state space
stochastic games
video games
kernel methods
markov chain
pattern recognition
learning algorithm