An Iterative Algorithm for Solving Constrained Decentralized Markov Decision Processes.

Aurélie Beynier Abdel-Illah Mouaddib

Published in: AAAI (2006)

Keyphrases

markov decision processes
dynamic programming
learning algorithm
policy iteration
search space
np hard
model based reinforcement learning
objective function
computational complexity
linear programming
state space
infinite horizon
probabilistic planning
decision theoretic planning
interval estimation