Value Function Based Reinforcement Learning in Changing Markovian Environments.

Balázs Csanád Csáji László Monostori

Published in: J. Mach. Learn. Res. (2008)

Keyphrases

reinforcement learning
real world
multi agent
complex environments
optimal policy
markov decision processes
highly dynamic
machine learning
learning algorithm
website
function approximation
reinforcement learning algorithms
policy gradient