Optimality principle broken by considering structured plant variation and relevant robust reinforcement learning.

Kei Senda Yurika Tani

Published in: SMC (2011)

Keyphrases

reinforcement learning
real world
multi agent
optimal solution
parameter tuning
structured data
machine learning
learning algorithm
learning process
robust estimation
function approximation
average reward
learning problems
markov decision processes
higher level
state space
control system
bayesian networks