An online POMDP algorithm for complex multiagent environments.

Sébastien Paquet Ludovic Tobin Brahim Chaib-draa

Published in: AAMAS (2005)

Keyphrases

optimal solution
computational complexity
dynamic programming
learning algorithm
np hard
online learning
computational efficiency
path planning
neural network
decision trees
objective function
multi agent
convex hull
belief state
single agent