Tank War Using Online Reinforcement Learning.

Kresten Toftgaard Andersen Yifeng Zeng Dennis Dahl Christensen Dung Tran

Published in: IAT (2009)

Keyphrases

reinforcement learning
online learning
real time
markov decision processes
function approximation
state space
temporal difference learning
genetic algorithm
case study
email
evolutionary algorithm
control system
dynamic programming
policy search
robotic control