Non-Adaptative Policies for 20 Questions Target Localization.

Ehsan Variani Kamel Lahouel Avner Bar-Hen Bruno Jedynak

Published in: CoRR (2015)

Keyphrases

database
optimal policy
target recognition
control policies
databases
neural network
social networks
reinforcement learning
multi agent systems
markov decision processes
target object
target tracking
answer questions