Improving Temporal Difference game agent control using a dynamic exploration during control learning.

Leo Galway Darryl Charles Michaela M. Black

Published in: CIG (2009)

Keyphrases

action selection
temporal difference
reinforcement learning
learning algorithm
td learning
learning process
temporal difference learning
e learning
active learning
partially observable
multi agent
learning environment
supervised learning
video games
reinforcement learning algorithms
learning agent