Brownian Snake Measure-Valued Markov Decision Process.

Zhenzhen Wang Hancheng Xing

Published in: ICSI (2) (2013)

Keyphrases

markov decision process
state space
optimal policy
infinite horizon
markov decision processes
long run
reinforcement learning
policy iteration
active contours
optimal control
transition probabilities
initial state
semi supervised
planning problems
finite horizon
transition matrices