Simulation-based optimization of Markov decision processes: An empirical process theory approach.

Rahul Jain Pravin Varaiya

Published in: Autom. (2010)

Keyphrases

markov decision processes
state space
reinforcement learning
finite state
optimal policy
policy iteration
transition matrices
dynamic programming
factored mdps
machine learning
state and action spaces
multistage
markov decision process
reachability analysis