Fast-Maneuvering Target Seeking Based on Double-Action Q-Learning.

Daniel C. K. Ngai Nelson Hon Ching Yung

Published in: MLDM (2007)

Keyphrases

action selection
reinforcement learning
cooperative
state action
multi agent
target tracking
function approximation
maneuvering target
optimal policy
reinforcement learning algorithms
evaluation function
data fusion
model free
learning algorithm
state space
moving objects
discounted reward