Finite-Step Approximation Error Bounds for Solving Average-Reward-Controlled Markov Set-Chains.

Hyeong Soo Chang

Published in: IEEE Trans. Autom. Control. (2008)

Keyphrases

error bounds
semi markov decision processes
reinforcement learning
worst case
theoretical analysis
probability distribution
long run
average reward
machine learning
upper bound
markov chain
random variables
markov decision processes
optimality criterion
polynomial time approximation