Towards a Deep Reinforcement Learning Approach for Tower Line Wars.

Per-Arne Andersen Morten Goodwin Ole-Christoffer Granmo

Published in: SGAI Conf. (2017)

Keyphrases

reinforcement learning
function approximation
state space
reinforcement learning algorithms
multi agent
robotic control
temporal difference
markov decision processes
line segments
learning process
learning algorithm
learning problems
model free
optimal policy
markov chain
belief nets
direct policy search