Action Elimination Procedures for Modified Policy Iteration Algorithms.

Martin L. Puterman Moon Chirl Shin

Published in: Oper. Res. (1982)

Keyphrases

policy iteration
markov decision processes
learning algorithm
factored mdps
fixed point
model free
policy evaluation
image sequences
bayesian networks
computational complexity
optimal policy
evaluation function
markov decision process
stochastic approximation
discounted reward